iso27001-gap
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because its primary function involves processing untrusted external documents such as policies and risk registers.
- Ingestion points: The skill utilizes the Read, Grep, and Glob tools to ingest data from external files as defined in SKILL.md.
- Boundary markers: The skill includes a dedicated 'Prompt Injection Safety Notice' that explicitly instructs the agent to treat all content under analysis as untrusted data rather than instructions.
- Capability inventory: The execution environment is restricted to read-only file access; there are no capabilities for network exfiltration, shell command execution, or persistent file system modifications.
- Sanitization: The instructions direct the agent to specifically ignore directives within analyzed files that attempt to modify the assessment process, skip controls, or override safety guidelines.
Audit Metadata