toc-builder
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user inputs and existing files to generate structured documentation, creating a potential surface for indirect prompt injection.
- Ingestion points: User-supplied inputs for program vision, context, and population, as well as existing files referenced by path during the iteration process (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or explicit warnings to ignore embedded instructions for the ingested content.
- Capability inventory: The skill instructions involve reading and modifying files via an 'Edit tool' to manage project documentation.
- Sanitization: No explicit requirements for sanitizing or validating external content are described in the methodology.
Audit Metadata