nist-csf
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied organizational details to generate gap assessments and profiles. While the skill has no executable capabilities that could be compromised, it does not explicitly define boundary markers or sanitization for these external inputs.\n
- Ingestion points: User-provided organizational context, mission statements, and security posture data described in
SKILL.md.\n - Boundary markers: Not specified in the skill instructions.\n
- Capability inventory: The skill contains no scripts, CLI tools, or network-capable functions.\n
- Sanitization: No explicit validation or escaping of user-provided content is implemented.\n- [SAFE]: The skill instructions and reference files are purely textual and provide legitimate cybersecurity framework alignment advice. No malicious patterns, obfuscation, or unauthorized access attempts were detected.
Audit Metadata