choosing-determinism
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and analyze external files including SKILL.md, referenced documents, and scripts to identify refactoring opportunities. This behavior creates a data ingestion surface for potentially untrusted content.
- Ingestion points: The agent is directed to read the target skill's SKILL.md, referenced files, and associated scripts.
- Boundary markers: The instructions do not define delimiters or provide specific guidance for the agent to treat the content of the analyzed files as untrusted data.
- Capability inventory: The agent possesses capabilities to read files, generate new script code, and modify existing skill definitions.
- Sanitization: The skill lacks procedures for sanitizing or validating the contents of the files before they are processed by the agent.
Audit Metadata