execute-with-spec
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to carry criteria from a 'frozen acceptance table' into sub-agent prompts, forming a 'fractal hand-off' chain.
- Ingestion points: Instructions in SKILL.md direct the agent to read and propagate data from an external 'frozen table' or 'spec'.
- Boundary markers: The instructions do not include the use of delimiters or explicit 'ignore' warnings to prevent the sub-agent from obeying instructions hidden in the spec.
- Capability inventory: This skill contains only markdown instructions and has no direct tools or executable scripts.
- Sanitization: There are no instructions provided for sanitizing or validating the content of the external spec before it is interpolated into prompts.
Audit Metadata