Skills
Navigate
skills/dmccreary/ibook-skills/learning-graph-generator/Gen Agent Trust Hub

learning-graph-generator

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions suggest cloning a sample textbook template from the author's GitHub repository to initialize the project environment. This is a vendor-owned resource.
  • Evidence: git clone https://github.com/dmccreary/intelligent-book-template in SKILL.md.
  • [COMMAND_EXECUTION]: The skill workflow requires executing several bundled Python scripts and a shell script to perform graph quality analysis, taxonomy assignment, and JSON schema validation.
  • Evidence: Execution patterns for analyze-graph.py, add-taxonomy.py, csv-to-json.py, and validate-learning-graph.sh described in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied course descriptions to generate concepts and labels. A malicious course description could attempt to influence the agent's behavior during this generation step.
  • Ingestion points: docs/course-description.md as specified in the Step 1 assessment process in SKILL.md.
  • Boundary markers: The skill does not explicitly define delimiters or 'ignore' instructions for the ingested content.
  • Capability inventory: The skill has file-system write access and the ability to execute the provided Python scripts.
  • Sanitization: Data is processed into structured CSV and JSON formats using the csv and json Python modules.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:06 AM