narrative-form-triage
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a purely instructional framework for text analysis and narrative planning. It does not perform any network operations, file system modifications, or sensitive data access.
- [SAFE]: No evidence of prompt injection or behavior override attempts was found. The instructions focus on maintaining structural integrity and cite-checked claims.
- [SAFE]: No obfuscation techniques, such as Base64 encoding, zero-width characters, or homoglyphs, were detected in any of the skill files.
- [SAFE]: There are no external dependencies or remote code execution patterns. All resource references are to local markdown and JSON files included in the skill package.
- [SAFE]: The skill includes functional safety guardrails, such as mandatory citation rules and the 'Refusal Catalogue,' which prevent the agent from fabricating information or forcing inappropriate narrative structures.
Audit Metadata