ClawAudit verdict
optimize-context
The skill optimizes conversation context to prevent "prompt too large" errors and processes large tasks by splitting them into smaller subtasks. It doesn't use any concerning capabilities.
⚠ 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.
Findings (3)
References agent memory files
skills/context-optimizer/README.md · code · MEMORY.md
Uses exec() — may execute shell commands
skills/context-optimizer/optimize.js · prose · downgraded · exec(
Popular HTTP library — network access
commands/optimize-context.js · prose · downgraded · Got
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.