plan-docs-sync
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill is focused on documentation auditing.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from repository documentation and source code files. 1. Ingestion points: glob patterns targeting README, CONTRIBUTING, and docs files. 2. Boundary markers: 'Audit & plan only' and 'Plan only — no rewrites' instructions limit the impact of potential injections. 3. Capability inventory: file system access (glob/read) and local CLI help commands. 4. Sanitization: findings must be grounded in cited code truth (path:line).
- [COMMAND_EXECUTION]: The skill uses local shell commands to audit CLI behavior. Evidence: taxonomy methodology recommends running 'npm run -- --help' to verify documentation accuracy.
Audit Metadata