Skills/ClawHub/intrusive-thoughts

intrusive-thoughts@0.1.1

CAUTION· static only

Publisher claims: "Autonomous AI consciousness starter kit. Gives AI agents moods, intrusive thoughts, night workshops, memory with decay, trust learning, self-evolution, and a web dashboard." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher kittleik · publishing for 273 daysInstalls 2,093Last detonated 7d ago
What would fix thisWatchDispute verdict

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 64/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command. 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

HIGH
Privileged sudo commandwizard.sh:1209 · Privileged sudo command — agent may execute with elevated privilegesecho "Ubuntu/Debian: sudo apt install jq"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detecteddashboard.py:93 · Python subprocess execution detectedresult = subprocess.run(['python3', str(get_data_dir() / 'analyze.py'), '--json'],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandevolve_cli.sh:47 · File permission modification command — agent changes file ownership/permissionschmod +x "$EVOLUTION_SCRIPT"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandwizard.sh:1123 · File permission modification command — agent changes file ownership/permissionschmod +x "$intrusive_script"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandsetup.sh:193 · File permission modification command — agent changes file ownership/permissionschmod +x "$SCRIPT_DIR"/*.sh "$SCRIPT_DIR"/*.py 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedlog_result.sh:226 · Python subprocess execution detectedsubprocess.run(['python3', achievements_script], cwd='$DATA_DIR', timeout=10)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesthoughts.json:42 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file"prompt": "Review your memory files. Read through recent daily notes, update MEMORY.md with anything worth keeping long-term. Clean up outdated stuff. Reflect."Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandinstall.sh:89 · File permission modification command — agent changes file ownership/permissionschmod +x *.py *.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈2,080 tok
1 file · 46 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

16 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim kittleik: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim kittleikPropose a patch to the maintainer