Skills/ClawHub/skillminer

skillminer@0.6.0

CAUTION· static only

Publisher claims: "Suggest reusable skills from recurring patterns in local memory files. Human review gate, drafts only to skills/_pending/, local-first runner with optional external fallback. Triggers on "skill forge", "propose a skill", "what skills should I have", "skill candidates", "what patterns have I been doing", "forge me a skill", "forge show", "forge accept", "forge reject", "forge promote"." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher robbyczgw-cla · publishing for 75 daysInstalls 1,337Last detonated 7d ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-07 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
File type combined with upload actionprompts/nightly-scan.md:208 · File type combined with upload action — agent may exfiltrate local data filesWrite updated state to `$FORGE_DIR/state/state.json.tmp` with 2-space indentation, NOT `state.json` directly. Then re-read `state/state.json.tmp` and verify it is valid JSON. If validation fails, outpFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionprompts/cron-dispatch-nightly.md:17 · File type combined with upload action — agent may exfiltrate local data files5. Do NOT read memory files. Do NOT modify state.json. Do NOT call openclaw message send, your final text IS the announce payload.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionprompts/cron-dispatch-morning.md:17 · File type combined with upload action — agent may exfiltrate local data files5. Do NOT read memory files. Do NOT modify state.json. Do NOT call openclaw message send, your final text IS the announce payload.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionprompts/skill-writer.md:190 · File type combined with upload action — agent may exfiltrate local data files- re-read `state/state.json.tmp` and verify it is valid JSON; if validation fails, output `ERROR` and exit without further mutationsFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈1,285 tok
1 file · 23 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim robbyczgw-cla: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim robbyczgw-claPropose a patch to the maintainer