calibre-study-notes
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to run a local script
scripts/legal-gate.mjsfor verifying content and usesnpxto validate Mermaid diagrams. - [EXTERNAL_DOWNLOADS]: Fetches the
@mermaid-js/mermaid-clipackage from the npm registry usingnpxduring the diagram validation phase. - [PROMPT_INJECTION]: 1. Ingestion points: Processes external text data from the Calibre library through
calibre_get_contentandcalibre_semantic_search(SKILL.md). 2. Boundary markers: The instructions mandate 'Own words everywhere' and a 'Compression floor,' which effectively prevents the agent from directly following instructions embedded in the source text (SKILL.md). 3. Capability inventory: Includes file system writing and shell execution capabilities (SKILL.md). 4. Sanitization: Relies on the generation of summaries and human-readable study notes to filter and process source content.
Audit Metadata