documenter-coauthoring
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external technical documents (PRDs, specs, proposals) which could contain adversarial instructions.
- Ingestion points: Reads user-supplied files and existing documentation in Workflow step 1.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the processed files.
- Capability inventory: No dangerous capabilities such as network access, system modification, or arbitrary command execution were identified in the skill scripts or instructions.
- Sanitization: There are no mentioned mechanisms for sanitizing or filtering instructions that might be embedded in the documentation being co-authored.
Audit Metadata