trope-manager
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions are limited to narrative analysis and ledger maintenance. There are no signs of command execution, privilege escalation, or persistence mechanisms. The skill does not reference any external network resources or third-party dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest narrative content for trope analysis, which constitutes a potential injection surface.
- Ingestion points: The skill reads story text and tropes to maintain a ledger in
themes/TROPE.mdas described in the coordination section. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the guidelines.
- Capability inventory: Capabilities are limited to local file read/write operations for documentation purposes. No network or shell execution tools are enabled.
- Sanitization: There is no explicit sanitization step for the story data being processed.
Audit Metadata