ClawAudit verdict

evolution-toolkit

evolution-toolkit-build

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The skill provides a toolkit for agent self-improvement. It does not exhibit any malicious behaviors and offers legitimate functionality for analyzing and optimizing agent performance.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

60
security
90
transparency
70
maintenance

Findings (6)

Pattern match high

Pipe to sh — executes piped content as shell commands

scripts/contradiction-scanner.js · prose · downgraded · |sh

Pattern match medium

Uses exec() — may execute shell commands

scripts/contradiction-scanner.js · prose · downgraded · exec(

Pattern match low

References agent memory files

config.example.json · prose · downgraded · MEMORY.md

Pattern match low

Popular HTTP library — network access

scripts/session-coherence.js · prose · downgraded · got

Pattern match low

Node http/https module — low-level network access

scripts/skill-optimizer.js · prose · downgraded · require('https')

Pattern match low

Accesses sensitive environment variables

scripts/skill-optimizer.js · prose · downgraded · process.env.GEMINI_API_KEY

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API