spec-simulate
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external specification files and source code. These untrusted inputs could contain hidden instructions intended to influence the agent's behavior or manipulate the implementation simulation.
- Ingestion points: Reads specification files, source files, tests, and APIs (SKILL.md).
- Boundary markers: There are no explicit instructions for using delimiters or boundary markers to separate external content from the agent's internal instructions.
- Capability inventory: The agent has the capability to read project files and write patches to specification files.
- Sanitization: No sanitization or input validation mechanisms are described for the external content being processed.
- Mitigation: The workflow includes a requirement to "Verify current behavior from code instead of relying on the spec's claims," which acts as a verification step against potentially deceptive specification content.
Audit Metadata