regression-sweep
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to analyze external and potentially untrusted data sources.
- Ingestion points: External project files including code callers, provider variants, documentation snippets, and generated artifacts (SKILL.md).
- Boundary markers: The skill does not provide instructions to use delimiters or "ignore previous instructions" warnings when reading external content.
- Capability inventory: The skill is intended for an agent with capabilities to read, search, and analyze a codebase, including child-process calls and subprocess arguments.
- Sanitization: There are no instructions to sanitize or validate the content retrieved from external sources before processing it.
Audit Metadata