tl-docs-audit
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes codebase files and documentation (ingestion points) to generate reports and propose/apply fixes (capability). Malicious instructions embedded in the audited content could influence the agent's behavior during the modification phase.
- Ingestion points: The skill scans multiple source files including
src/,config/,drizzle/schema.ts, anddocs/in Phases 1, 2, and 3. - Boundary markers: There are no explicit delimiters or instructions defined to isolate the audited content from the agent's operational logic.
- Capability inventory: The skill has file-writing capabilities in Phase 5 to apply documentation fixes.
- Sanitization: No sanitization or content validation is performed on the ingested documentation text.
- [COMMAND_EXECUTION]: The skill references and provides examples for integrating external CLI tools like
linkinator,vale,alex, andmarkdownlint. While these are well-known developer utilities, they represent points of command execution that interact with the local environment.
Audit Metadata