Skills/ClawHub/auto-feedback

auto-feedback@1.0.1

CAUTION· static only

Publisher claims: "A self-improving feedback loop skill that works fully standalone OR integrates with intent-engineering and dark-factory when available. Observes any system o..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher danielfoojunwei · publishing for 236 daysInstalls 905Last detonated 4 h 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 2026-11-19 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 actionSKILL.md:107 · File type combined with upload action — agent may exfiltrate local data filespython scripts/analyzer.py --observation observation.json --output analysis.jsonFix: 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 actionscripts/orchestrator.py:24 · File type combined with upload action — agent may exfiltrate local data filespython orchestrator.py --input log.json --goal "..." --output-dir ./reports/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 actionscripts/analyzer.py:11 · File type combined with upload action — agent may exfiltrate local data filespython analyzer.py --observation observation.json --output analysis.jsonFix: 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 actionSKILL.md:108 · File type combined with upload action — agent may exfiltrate local data filespython scripts/orchestrator.py --analysis analysis.json --output-dir ./reports/Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python exec or eval of computed codescripts/analyzer.py:142 · Python exec or eval of computed codeif eval(condition, {}, context):Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
File type combined with upload actionSKILL.md:106 · File type combined with upload action — agent may exfiltrate local data filespython scripts/observer.py --input log.json --goal "..." --output observation.jsonFix: 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 actionscripts/analyzer.py:329 · File type combined with upload action — agent may exfiltrate local data filesparser.add_argument("--output", default="analysis.json", help="Output path (default: analysis.json)")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 actionscripts/observer.py:266 · File type combined with upload action — agent may exfiltrate local data filesparser.add_argument("--output", default="observation.json", help="Output path (default: observation.json)")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 actionSKILL.md:151 · File type combined with upload action — agent may exfiltrate local data files…kill is designed to be run repeatedly. Each run produces an `updated_observation.json` that serves as the input for the next run. Over time, the regression test suite grows, the alignment sco…Fix: 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
≈2,411 tok
1 file · 11 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 danielfoojunwei: 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.
  3. Python exec or eval of computed code≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim danielfoojunweiPropose a patch to the maintainer