simready-foundation-conform-fet-024-standard
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes external files and validation reports to determine its actions.
- Ingestion points: The workflow in
SKILL.mdreads and follows instructions from profile TOML files, validation reports, and user-provided inputs inWorkflowsteps 1 and 2. - Boundary markers: No explicit delimiters or instructions are present to prevent the agent from following malicious instructions potentially embedded in the validation reports or input assets.
- Capability inventory: The skill has the capability to write to the file system (staged output in Step 4) and execute validation commands (profile gates in Step 6).
- Sanitization: The instructions do not specify any sanitization or validation logic for data ingested from the reports before it is used to guide the repair process.
Audit Metadata