simready-foundation-conform-fet-021-isaac
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute validation tools, referred to as 'profile gates' or 'capability validation gates', to verify the success of repairs.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of validation reports and profile TOML files to determine its actions.
- Ingestion points: Validation reports, profile TOML files, and user-provided requests (SKILL.md).
- Boundary markers: The instructions do not specify explicit delimiters or warnings to ignore embedded instructions within the ingested data.
- Capability inventory: The skill has the ability to write to files (repairing assets) and execute shell commands (validation gates) (SKILL.md).
- Sanitization: There is no mention of input validation or sanitization for the content of the reports or profiles.
Audit Metadata