narrative-registry
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions and metadata are free from malicious patterns, obfuscation, or unauthorized capability requests.
- [EXTERNAL_DOWNLOADS]: The skill references the author's official GitHub repository as its project homepage.
- [PROMPT_INJECTION]: The skill identifies and mitigates a potential surface for indirect prompt injection arising from the processing of external brand content.
- Ingestion points: The skill ingests user-provided text and candidate data from the
memory/narrative-registry/directory. - Boundary markers: The instructions include explicit directives to treat all external material as untrusted data rather than instructions, referencing the project's security protocol.
- Capability inventory: Capabilities are restricted to writing text to specific local files (e.g.,
canon.md,versions.md,candidates.md). No network access or code execution tools are requested. - Sanitization: The logic explicitly prohibits untrusted data from influencing administrative registry functions, such as version control or term approval lists.
Audit Metadata