just-spec
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from local documentation files which may contain embedded instructions intended to influence the agent's behavior.
- Ingestion points: The skill reads
docs/scope-*.mdanddocs/design-*.mdfiles from the repository, which may contain attacker-controlled content. - Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to treat the document content as data only.
- Capability inventory: The agent's capabilities include reading arbitrary code and test files in the repository and writing new documentation files to the file system.
- Sanitization: No validation or sanitization of the input file content is defined before the agent incorporates it into the final specification.
Audit Metadata