teach
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external content from sources documented in RESOURCES.md to generate lessons and glossary definitions.\n
- Ingestion points: External URLs and content linked in RESOURCES.md and user inputs in MISSION.md.\n
- Boundary markers: Absent; the agent is not instructed to use specific delimiters for untrusted content.\n
- Capability inventory: Write access to the local workspace (./lessons/, ./assets/, etc.) and command execution for opening generated files.\n
- Sanitization: Absent; no explicit requirement to sanitize external resource data before interpolation.\n- [DYNAMIC_EXECUTION]: The agent dynamically generates interactive HTML files and shared components (e.g., simulators, quizzes) stored in the ./assets/ and ./lessons/ directories.\n- [COMMAND_EXECUTION]: The skill includes instructions to use a CLI command to open generated lesson files for the user.
Audit Metadata