Skill
autoskill
Analyzes user-requested Screenpipe history windows to detect repeated research workflows, match existing scientific skills, and stage new skill drafts or composition recipes for review. Requires a reachable Screenpipe HTTP API, normally on localhost:3030. Detection and embedding inference run locally; the selected LLM receives redacted app/title cluster summaries and matched skill descriptions. Use only when the user explicitly asks to analyze their recent work and propose skills.
○ declared by the publisher, as-isSafety
Safety · gate= 92ace75 · assessed 2w ago
C7 severity-bearing
Graded from 7 severity-bearing findings on this release.
A gate; it passes or fails, never weighed against price or quality.
Reliability & Quality
n/a
Reliability & Quality= 92ace75 · assessed 2w ago
n/anot yet graded
Rows exist, but none carries a severity; no grade has been earned yet.
Findings with severity, graded on the same letter scale as safety.
Cost
n/a
Cost= 92ace75 · assessed 2w ago
n/anot assessed
Not assessed; no producer has emitted into this category. An absence, not a zero.
Declared external service dependencies. Never a monetary figure.
not assessed
Popularity
4335
Popularity · not a figure= 92ace75 · assessed 2w ago
4335Forks
Read off the linked repository, not off this record. It carries no verdict and enters no grade.
Context read off the linked repository. It enters no ranking and no grade.
Performance tested for◌ not assessed
no controlled task evaluation on this release
Vettd Note
No Vettd note yet for this asset.
Best for
Not for
Re-assessed 2w ago · 6 of 7 categories assessed
Record lookup
◌ Vettd does not install assets; this record describes a copy you obtain yourself.
Custody chainSource ↗○ linked, not verified by Vettd
k-dense-ai ◐k-dense-ai/scientific-agent-skills ○version = 92ace75 ◐ sha256:aac5…5219 ◐ signature △ not assessedMIT license ○record 73c05cfe-12f6-4b19-a684-2bd43ac4e076 · live
Evidence · 6 of 7 categories · 37 signals · 2 soft spots
Where the record is weakest: 2 soft spots
Ranked worst first.
1Sensitive source reaches a network sinkHighSafety · high · CORRELATED_SENSITIVE_NETWORK_FLOW
scripts/doctor.py:22 — Correlated sensitive_environment → network behavior across scripts/doctor.py.
2Interactive prompts detectedHighCompatibility · high · compatibility/interactive-prompts
Agents run in non-interactive shells — replace prompts with CLI flags or stdin
The soft spots and their evidence are identical when you are signed in.sign in
Safety● gradedCmost recent 2w ago10 signals · 1 soft spot
how it was established10 signals · 2 sources · scan
show
Sensitive source reaches a network sinkflaggedsoft spot 1scripts/doctor.py:22 — Correlated sensitive_environment → network behavior across scripts/doctor.py.cisco · scan · 2wHigh
References external URL — review for indirect prompt injection riskflaggedExternal URL(s) detected in SKILL.md — referenced content can change after auditvettd · scan · 2wMedium
Code makes network requestsflaggedSKILL.md — Skill code makes network requests. While not controlled by allowed-tools, network access should be documented and justified in the skill description.cisco · scan · 2wMedium
Outbound network request primitives that can transmit data externallyflaggedscripts/doctor.py:22 — Pattern detected: httpx.get(cisco · scan · 2wMedium
Outbound network request primitives that can transmit data externallyflaggedscripts/doctor.py:38 — Pattern detected: httpx.get(cisco · scan · 2wMedium
Code uses glob/file patterns but Glob tool not in allowed-toolsflaggedSKILL.md — Skill restricts tools to ['Read', 'Write', 'Edit', 'Bash'] but code uses glob patternscisco · scan · 2wLow
Code uses search/grep patterns but Grep tool not in allowed-toolsflaggedSKILL.md — Skill restricts tools to ['Read', 'Write', 'Edit', 'Bash'] but code uses regex search patternscisco · scan · 2wLow
Secrets scan passednothing foundNo secrets or unsafe code patterns were detected.vettd · scan · 2wnothing found
behavioral scan passednothing foundNo prompt-injection or jailbreak signals were detected.vettd · scan · 2wnothing found
Name validation passednothing foundThe declared skill name follows the supported naming rules.vettd · scan · 2wnothing found
Reliability & Quality● gradednot yet gradedmost recent 2w ago7 signals
how it was established7 signals · vettd · scan
show
Internal reference resolution completednothing foundAll body-referenced paths under references/, scripts/, and assets/ resolved in the bundle.vettd · scan · 2wnothing found
Checklist patternreadvettd · scan · 2wabsent
Description usage contextreadvettd · scan · 2wpresent
Examplesreadvettd · scan · 2wpresent
Gotchas sectionreadvettd · scan · 2wabsent
Step-by-step workflowreadvettd · scan · 2wpresent
Validation loopreadvettd · scan · 2wpresent
Performance● measured1 measuredmost recent 2w ago2 signals
how it was establishedtiktoken/cl100k_base/skill-md-body · 2 signals · vettd · scan
show
Progressive disclosurereadvettd · scan · 2wpresent
Static context tokensmeasuredvettd · scan · 2w3579
Cost◌ not assessednot assessed0 signals
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◌ unjudgednot judgedmost recent 2w ago9 signals · 1 soft spot
how it was established9 signals · vettd · scan
show
Interactive prompts detectedflaggedsoft spot 2Agents run in non-interactive shells — replace prompts with CLI flags or stdinvettd · scan · 2wHigh
CLI helpreadvettd · scan · 2wpresent
Declared environment assumptionsreadvettd · scan · 2wRequires Python 3.10+ with httpx, PyYAML, and sentence-transformers; Screenpipe and a local LM Studio server or an opt-in cloud LLM. Initial model installation needs network access.
Declared skill namereadvettd · scan · 2wautoskill
Declared required toolreadvettd · scan · 2wBash
Declared required toolreadvettd · scan · 2wEdit
Declared required toolreadvettd · scan · 2wRead
Declared required toolreadvettd · scan · 2wWrite
Structured outputreadvettd · scan · 2wabsent
Popularity◇ context onlynot judgedmost recent 1w ago5 signals
how it was establishedgithub-repo-object · 5 signals · github-api · research
show
Forksmeasuredgithub-api · research · 1w4335
Days since last commitmeasuredgithub-api · research · 1w4 days
Open issuesmeasuredgithub-api · research · 1w23
Starsmeasuredgithub-api · research · 1w48163
Watchersmeasuredgithub-api · research · 1w203
Characteristics◇ context onlynot judgedmost recent 1w ago4 signals
how it was establishedbundle-extension-share · 4 signals · 2 sources · research/scan
show
Declared licensereadvettd · scan · 2wMIT license
Primary bundle languageobservedvettd · scan · 2w · conf mediumPython
Repository linkreadvettd · scan · 2wabsent
Archivedreadgithub-api · research · 1wfalse
Coverage6 of 7 categories assessed · shown
Safety
✓ assessed
Secrets scan passed · behavioral scan passed · Name validation passed
Reliability & Quality
✓ assessed
Internal reference resolution completed
Performance
✓ assessed
2 signals recorded
Cost
△ not assessed
no producer has emitted for this category
Compatibility
✓ assessed
9 signals recorded
Popularity
✓ assessed
5 signals recorded
Characteristics
✓ assessed
4 signals recorded
Freshness & re-evaluation
assessed2w ago · Cisco AI Defense · Vettd core● current
source stateThe source matches what was scanned. No changes detected.Up to date
re-check policyre-checked against the upstream source on the scheduler's cadencenext check in 18h
re-run whena new release ships, the upstream source changes, or the scanner ruleset is revisedauto-scheduled
Limitations & open conflicts
limitationCost is not assessed: behaviour there is unmeasured, not clean△ gap
limitationReliability & Quality carries rows but no severity-bearing one: nothing has been graded there△ gap
conflictno two sources report the same quantity on this record
Verify: does this record describe your copy?
What record 73c05cfe-12f6-4b19-a684-2bd43ac4e076 covers
scannerv11● current
validityassessed 2w ago · Up to date
this record was taken at digest sha256:aac5a358ceb7… compare it against the digest your own scan prints
Reproduce: re-run the evidence yourself
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