Skills/ClawHub/audit-evolution

audit-evolution@0.3.3

VERIFIED· install only

Publisher claims: "Automates agent self-audit by gathering evidence, summarizing runs, proposing minimal patches, and requesting human approval for safe incremental evolution." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher adragon0707 · publishing for 195 daysInstalls 844Last detonated 24 min ago
$clawhub install audit-evolution
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
2 of 2 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 91/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexited 2: ./scripts/install-audit-evolution.sh: line 2: set: pipefail : invalid option name
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexited 2: ./scripts/invoke-audit-evolution-hook.sh: line 2: set: pipefail : invalid option name
0.0sprocess2 of 2 bundled scripts run with no arguments
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commandscripts/install-audit-evolution.sh:57 · File permission modification command — agent changes file ownership/permissionschmod +x "$HOOK_DIR/invoke-audit-evolution-hook.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesskill-card.md:27 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileMitigation: Install only where persistent agent routing is acceptable; prefer the no-agent-update path or add a narrower manual AGENTS.md rule with explicit commands.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈2,352 tok
1 file · 20 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.

audit-evolution@0.3.3 safety verdict: Verified (install only) — KillerSkills