◌ Vettd does not install assets; this record describes a copy you obtain yourself.
Custody chain○ no source link recorded
Unknown author◐→repo △ not assessed→version = △ no commit pinned→sha256:cmro…szi4◐→signature △ not assessed|license △ none declaredrecord 34d15432-87da-4c4d-9b14-d7b372e273c0 · live
◌ public recordYou are signed out, so you see the record and nothing else. sign in
▲References external URL — review for indirect prompt injection riskflaggedExternal URL(s) detected in SKILL.md — referenced content can change after auditvettd · scan · 3moMedium
▲CLI help supportedflaggedscripts/drug/scene-hotwords.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/feedback/app-detail.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/speech/speech-records.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/training-flow/records.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/training/records-detail.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲No repository linkflaggedNo repository field found in SKILL.md frontmatter. Skills without a verifiable source repository cannot be externally audited.vettd · scan · 3moInfo
▲Structured output formatflaggedscripts/feedback/app-detail.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/training/records.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/dialogue-flow/get-flow-detail.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/gpts/session.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/gpts/training-feedback.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/home/summary.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/scene-image/reset.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/speech/speech-finish.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Description too briefflaggedA few sentences covering scope and trigger conditions improves activation accuracyvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/drug/scene-list-by-drug.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/training/my-stats.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/basic/gpt-id.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/basic/gpt-id.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/drug/scene-list-by-drug.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/home/product-scenes.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/learning/video-progress-get.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/prepare/opening-guidance.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/dialogue-flow/get-flow-detail.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/feedback/gpt-id.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/speech/speech-detail.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/speech/speech-detail.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/training/records.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲No evaluation test casesflaggedAdd an evals/ directory with test prompts and expected outputs to measure skill qualityvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/drug/scene-list.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/gpts/training-interact.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/home/product-scenes.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/learning/video-detail.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/speech/speech-finish.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲No prompt injection or jailbreak signals detectedflaggedScanned text content for instruction override, jailbreak framing, credential solicitation, and embedded injection markersvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/basic/tts-config.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/drug/scene-doctor-titles.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/gpts/del-user-token.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/gpts/app-detail.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/gpts/app-detail.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/gpts/speech-feedback.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/gpts/speech-feedback.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/gpts/sse-suggest.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/gpts/sse-suggest.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/prepare/opening-guidance-clear.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/training-flow/scenes.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲No secrets or unsafe code patterns detectedflaggedScanned all files for credentials, private keys, and code-level risks (eval, shell exec, destructive ops)vettd · scan · 3moInfo
▲Progressive disclosure usedflaggedSKILL.md body references files in references/, scripts/, or assets/ — agents can load additional context on demand instead of consuming everything upfrontvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/drug/drug-list.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲CLI help supportedflaggedscripts/drug/scene-list.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/prepare/opening-guidance.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
▲Structured output formatflaggedscripts/training-flow/drugs.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
Not assessed; no producer has emitted into reliability & quality for this asset. That is different from a check that ran and found nothing, which the record would carry as a row of its own.
+Performance◌ not assessednot assessed0 signalsrecord 34d15432-87da-4c4d-9b14-d7b372e273c0
how it was establishednot assessed; no producer has emitted into this category
Not assessed; no producer has emitted into performance for this asset. That is different from a check that ran and found nothing, which the record would carry as a row of its own.
+Cost◌ not assessednot assessed0 signalsrecord 34d15432-87da-4c4d-9b14-d7b372e273c0
how it was establishednot assessed; no producer has emitted into this category
Not assessed; no producer has emitted into cost for this asset. That is different from a check that ran and found nothing, which the record would carry as a row of its own.
+Compatibility◌ not assessednot assessed0 signalsrecord 34d15432-87da-4c4d-9b14-d7b372e273c0
how it was establishednot assessed; no producer has emitted into this category
Not assessed; no producer has emitted into compatibility for this asset. That is different from a check that ran and found nothing, which the record would carry as a row of its own.
+Popularity◌ not assessednot assessed0 signalsrecord 34d15432-87da-4c4d-9b14-d7b372e273c0
how it was establishednot assessed; no producer has emitted into this category
Not assessed; no producer has emitted into popularity for this asset. That is different from a check that ran and found nothing, which the record would carry as a row of its own.
+Characteristics◌ not assessednot assessed0 signalsrecord 34d15432-87da-4c4d-9b14-d7b372e273c0
how it was establishednot assessed; no producer has emitted into this category
Not assessed; no producer has emitted into characteristics for this asset. That is different from a check that ran and found nothing, which the record would carry as a row of its own.
cms-tbs-training/SKILL assessed 3mo ago /
87 signals · 1 category
Safety
▲References external URL — review for indirect prompt injection riskMedium
▲CLI help supportedInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲No repository linkInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲Structured output formatInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲Valid name fieldInfo
▲Structured output formatInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲SKILL.md body length is reasonableInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲Structured output formatInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲Description lacks usage contextInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲Structured output formatInfo
▲Description within character limitInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲SKILL.md presentInfo
▲Description too briefInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲Structured output formatInfo
▲No evaluation test casesInfo
▲Structured output formatInfo
▲Structured output formatInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲No prompt injection or jailbreak signals detectedInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲No secrets or unsafe code patterns detectedInfo
▲Progressive disclosure usedInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲Structured output formatInfo
▲scripts/ directory presentInfo
▲Examples includedInfo
▲Structured output formatInfo
▲Structured output formatInfo
▲Structured output formatInfo
▲Structured output formatInfo
▲Step-by-step workflow foundInfo
▲CLI help supportedInfo
▲CLI help supportedInfo
▲Structured output formatInfo
▲Structured output formatInfo
‹ › or arrow keys move through 87
Coverage1 of 7 categories assessed · shown
Safety
✓ assessed
assessed as findings and a letter grade, not as signals
Reliability & Quality
△ not assessed
no producer has emitted for this category
Performance
△ not assessed
no producer has emitted for this category
Cost
△ not assessed
no producer has emitted for this category
Compatibility
△ not assessed
no producer has emitted for this category
Popularity
△ not assessed
no producer has emitted for this category
Characteristics
△ not assessed
no producer has emitted for this category
Freshness & re-evaluation
assessed3mo ago · Vettd core○ untracked
source stateThis asset is not yet covered by scheduled change detection.
re-check policyno re-check is scheduled for this assetnot scheduled
re-run whena new release ships, the upstream source changes, or the scanner ruleset is revisednot scheduled
Limitations & open conflicts
limitationReliability & Quality, Performance, Cost, Compatibility, Popularity, Characteristics are not assessed: behaviour there is unmeasured, not clean△ gap
conflictno two sources report the same quantity on this record
Verify: does this record describe your copy?
What record 34d15432-87da-4c4d-9b14-d7b372e273c0 covers
scannerv1△ superseded by v11
validityassessed 3mo ago · Staleness unknown
$vettd scan folder <path>
this record was taken at digest sha256:cmrodgpfr0d5… compare it against the digest your own scan prints
Reproduce: re-run the evidence yourself
$vettd scan folder /path/to/your/copy
runs the same scanners against your own copy; the published record is never overwritten
How this record comparesagainst other published records · full comparison →
Signal kinds
▲ finding: something to act on, carries a severity● measurement: a reproducible quantityƒ estimate: inferred from a sample▪ fact: read directly off the artifact◆ classification: assigned from a taxonomy◌ nothing found: a producer looked and emitted no object◇ context only: described, never graded
Custody marks
◐ computed by vettd○ declared by the publisher, as-is△ not assessed: nothing looked
Weigh cms-tbs-training/SKILL against other published skills: the safety grade, its finding counts and each category’s verdict, one row apiece. The full comparison page carries every signal and framework coverage.