simplify
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the repository, including source code and instructions, which creates a surface where embedded malicious instructions could influence agent behavior.
- Ingestion points: The workflow in
SKILL.mdexplicitly reads repository instructions, code, callers, and tests. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the data read from the repository.
- Capability inventory: The skill allows the agent to modify files and execute local development tools like linters, typecheckers, and unit tests.
- Sanitization: The skill documentation does not outline methods for sanitizing or validating the contents of the repository files it processes.
Audit Metadata