The Agent Skills Directory

[SAFE]: No malicious patterns or security threats were detected. The skill's functionality is limited to reading project documentation and code diffs to generate or update descriptive functional maps.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it ingests untrusted data from git diffs, design documents, and plan files. However, the risk is considered minimal and acceptable given that the skill's capabilities are restricted to producing documentation updates. * Ingestion points: docs/routespec/ files, git diff, plan.md, design.md, and user instructions. * Boundary markers: Not present. * Capability inventory: Limited to file read and write operations for documentation purposes. * Sanitization: No explicit sanitization or filtering of input content is mentioned.

route-sync