teach
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use CLI commands to open generated files for the user, which involves interacting with the system shell. Evidence: In SKILL.md, it states: 'If possible, open the lesson file for the user by running a CLI command.'
- [INDIRECT_PROMPT_INJECTION]: The skill relies on reading and processing various markdown and HTML files from the local workspace which could contain malicious instructions if populated from untrusted sources. * Ingestion points: MISSION.md, RESOURCES.md, NOTES.md, ./learning-records/.md, and ./reference/.html. * Boundary markers: The instructions do not define delimiters or warnings to ignore instructions within these files. * Capability inventory: The agent is instructed to perform file system writes and execute CLI commands. * Sanitization: No sanitization or validation of the ingested content is specified.
- [DYNAMIC_EXECUTION]: The agent is tasked with creating and managing interactive components that are executed in a browser context. Evidence: SKILL.md mentions the creation of 'quiz widgets, simulators, diagram helpers' in the ./assets/ directory.
Audit Metadata