simready-foundation-conform-fet-006-standard
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local JSON manifests and Markdown files, which serves as an attack surface for instructions embedded in data.
- Ingestion points: Reads FET_006_STANDARD manifests and documentation from nv_core/tiers/simready_foundation_tier_core/.
- Boundary markers: Absent; the skill does not specify delimiters to distinguish between data and instructions.
- Capability inventory: The skill allows file writing to staged output locations and execution of validation commands.
- Sanitization: Absent; the agent is instructed to treat the JSON manifests as authoritative for its logic.
- [COMMAND_EXECUTION]: The workflow involves running validation tools to verify asset repairs.
- Evidence: The skill instructs the agent to rerun the same profile gate and record the validation command used in the final report.
Audit Metadata