explain-concepts
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (LOW): The methodology file references the execution of a local Python script
tools/generate_image.py. This command is explicitly tied to the primary purpose of the skill (generating educational diagrams) and includes a requirement to ask the user for permission before execution. - [Indirect Prompt Injection] (LOW): The skill is designed to process untrusted user input (arbitrary concepts/topics) to generate explanations.
- Ingestion points: User-provided concepts in
references/methodology.mdtemplates. - Boundary markers: The skill uses structured 'Explanation Modes' and markdown templates to constrain the output format.
- Capability inventory: Access to
WebSearchand local script execution (tools/generate_image.py). - Sanitization: Relies on the host AI agent's internal safety filters for user-provided topics.
Audit Metadata