iso-42001-ai-governance
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill files (SKILL.md, references/audit-procedure.md, and references/report-template.md) contain only documentation, checklists, and reporting templates. No scripts, automated shell commands, or network requests are defined within the skill content.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze potentially untrusted external documentation provided by the user.\n
- Ingestion points: The skill accepts
ai_system_description,use_case, andexisting_documentationas inputs inSKILL.md.\n - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing input documentation.\n
- Capability inventory: No dangerous capabilities such as subprocess calls, file-writing tools, or network operations are invoked by the skill itself in any of the provided files.\n
- Sanitization: There are no specific sanitization or validation mechanisms defined for the input data.\n
- Since the skill lacks executable code or automated tool usage based on the input, the risk from this surface is considered negligible.
Audit Metadata