Vvettd.
AddSign in

zeroclaw

zeroclaw-labs/zeroclaw/.claude/skills/zeroclawOpen on GitHub
From the author

Help users operate and interact with their ZeroClaw agent instance — through both the CLI (`zeroclaw` commands) and the REST/WebSocket gateway API. Use this skill whenever the user wants to: send messages to ZeroClaw, manage memory or cron jobs, check system status, configure channels or providers, hit the gateway API, troubleshoot their ZeroClaw setup, build from source, or do anything involving the `zeroclaw` binary or its HTTP endpoints. Trigger this even if the user just says things like 'check my agent status', 'schedule a reminder', 'store this in memory', 'list my cron jobs', 'send a message to my bot', 'set up Telegram', 'build zeroclaw', or 'my bot is broken' — these are all ZeroClaw operations.

Compare
SkillApache-2.04 filesHas referencesNo scriptszeroclaw-labs/zeroclaw
Overall scoreOverall score BOverall score on A, B, C, F (there is no D).
Security severityMedium1 security findingfrom 2 of 2 scanners

Static checks cannot guarantee safety.

Medium References external URL — review for indirect prompt injection risk

Open the leading finding →
Assessed Oct 28, 2026Content hashA Git tree SHA of the skill's folder. It identifies the files that were assessed. It is not a commit. e9f9b21Source unchanged, checked Oct 28, 2026
Historical result (archived, not the current assessment)
Source badge at capture
Archived Warn as archived

Archived explanation: Skill has warnings: 1 warning in security or structure checks.

Pass and Fail now belong to Framework checks.

Scanners, signals and record facts
Assessed
Oct 28, 2026
Content hashA Git tree SHA of the skill's folder. It identifies the files that were assessed. It is not a commit.
e9f9b21
Next source check
Oct 29, 2026
Files
4 in the skill, 1 with findings (File structure)
Record ID
c15a492
Reliability & quality
Findings list
No quality findings
Static context tokens
Measured from SKILL.md
3,643 tokens in the SKILL.md body
Progressive disclosure: present
Cost
Measured
Not assessedVettd does not assess cost yet.
Compatibility
Captured declarations and checks
Name zeroclaw
Environment needs : no valueNot declared by the author.
Popularity
Repository activity
★ 33.1k
Characteristics
Classified
Not assessedVettd does not assess characteristics yet.

Which scanners reported what

ScannerRunSecurity severity reportedSecurity findingsOther findingsNotes
vettdCompletedMedium100
ciscoCompletedInformational001

The overall score is B: 1 medium finding. It counts findings in every category. Security severity is Medium, the highest security finding across the scanners that ran (vettd reported medium; cisco reported informational). No captured run is recorded for snyk, socket and gen-trust-hub.

AssessmentFile structure 1Findings 1VersionsDisputes

Security findings

1 medium

Conflicting information. The author lists the license as Apache-2.0, but the cisco scanner reports that the skill manifest has no license field. Check the repository before you rely on either.

What this assessment does not cover

Static checks only, not a safety guarantee. What this does not cover
  • Static checks only. Nothing in the skill was run.
  • Pages linked from SKILL.md were not fetched or checked.
  • This record is not signed yet, so you can't verify it came from Vettd unchanged.
  • Name, description, author, version and license are shown as the author wrote them. Vettd didn't verify them.
  • Cost, runtime characteristics and usage are not assessed.
  • Framework checks (OWASP Top 10 for LLM Applications 2025): not assessed for this record.

What “Not assessed” means

zeroclaw

zeroclaw-labs/zeroclaw/.claude/skills/zeroclaw
Open on GitHub
From the author

Help users operate and interact with their ZeroClaw agent instance — through both the CLI (`zeroclaw` commands) and the REST/WebSocket gateway API. Use this skill whenever the user wants to: send messages to ZeroClaw, manage memory or cron jobs, check system status, configure channels or providers, hit the gateway API, troubleshoot their ZeroClaw setup, build from source, or do anything involving the `zeroclaw` binary or its HTTP endpoints. Trigger this even if the user just says things like 'check my agent status', 'schedule a reminder', 'store this in memory', 'list my cron jobs', 'send a message to my bot', 'set up Telegram', 'build zeroclaw', or 'my bot is broken' — these are all ZeroClaw operations.

Overall scoreOverall score BOverall score on A, B, C, F (there is no D).
Security severityMedium1 security findingfrom 2 of 2 scanners

Static checks cannot guarantee safety.

Medium References external URL — review for indirect prompt injection risk

Open the leading finding →
Assessed Oct 28, 2026Content hashA Git tree SHA of the skill's folder. It identifies the files that were assessed. It is not a commit. e9f9b21Source unchanged, checked Oct 28, 2026
Historical result (archived, not the current assessment)
Source badge at capture
Archived Warn as archived

Archived explanation: Skill has warnings: 1 warning in security or structure checks.

Pass and Fail now belong to Framework checks.

Compare
Full record · metadata, license, scanners and provenance
Assessed
Oct 28, 2026
Content hashA Git tree SHA of the skill's folder. It identifies the files that were assessed. It is not a commit.
e9f9b21
Next source check
Oct 29, 2026
Files
4 in the skill, 1 with findings (File structure)
Record ID
c15a492
SkillApache-2.04 filesHas referencesNo scriptszeroclaw-labs/zeroclaw
Security severity
Derived from findings
Medium
1 security finding
from 2 of 2 scanners
Reliability & quality
Findings list
No quality findings
Static context tokens
Measured from SKILL.md
3,643 tokens in the SKILL.md body
Progressive disclosure: present
Cost
Measured
Not assessedVettd does not assess cost yet.
Compatibility
Captured declarations and checks
Name zeroclaw
Environment needs : no valueNot declared by the author.
Popularity
Repository activity
★ 33.1k
Characteristics
Classified
Not assessedVettd does not assess characteristics yet.
Cost and characteristics: not assessedVettd does not assess cost or runtime characteristics yet.Usage: not assessedVettd does not record how often a skill is used.

Which scanners reported what

The overall score is B: 1 medium finding. It counts findings in every category. Security severity is Medium, the highest security finding across the scanners that ran (vettd reported medium; cisco reported informational).

vettdMedium1 security finding
ciscoInformational0 security findings
AssessmentFile structure 1Findings 1VersionsDisputes

Not covered

Static checks only. Linked pages not fetched. Record not signed yet. Author details not verified. Framework checks not assessed.