The Agent Skills Directory

[PROMPT_INJECTION]: No malicious patterns or bypass instructions were detected. The skill has an inherent attack surface for indirect prompt injection given its purpose.
Ingestion points: Reads project manifests, script headers, and config files (e.g., package.json, .env.example).
Boundary markers: None explicitly defined for untrusted data interpolation.
Capability inventory: Writes documentation files and executes local validation tools (e.g., pnpm lint).
Sanitization: Applies standard markdown formatting and writing guidelines.
[DATA_EXFILTRATION]: No exfiltration or exposure of sensitive data was found. Data ingestion is restricted to public configuration and source documentation headers.
[REMOTE_CODE_EXECUTION]: No remote code execution or suspicious external downloads from unknown sources were identified.
[COMMAND_EXECUTION]: The skill recommends standard local commands for project maintenance and verification tasks.

tl-docs-create