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.mjs for verifying content and uses npx to validate Mermaid diagrams.
  • [EXTERNAL_DOWNLOADS]: Fetches the @mermaid-js/mermaid-cli package from the npm registry using npx during the diagram validation phase.
  • [PROMPT_INJECTION]: 1. Ingestion points: Processes external text data from the Calibre library through calibre_get_content and calibre_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
Risk Level
SAFE
Analyzed
Aug 26, 2026, 12:55 AM
Security Audit — agent-trust-hub — calibre-study-notes