teach
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external resources (URLs) to generate lessons and learning records. This creates a surface for indirect prompt injection if a resource contains malicious instructions.
- Ingestion points: The agent reads external content from links identified during research and stored in
RESOURCES.mdto build the knowledge base. - Boundary markers: There are no specific delimiters or "ignore embedded instructions" warnings mentioned to wrap untrusted data before processing.
- Capability inventory: The skill has the ability to write files (HTML and Markdown) and execute shell commands to open files for the user.
- Sanitization: No explicit sanitization or validation of external content is described before interpolation into lessons.
- [COMMAND_EXECUTION]: The instructions direct the agent to run CLI commands to open the generated lesson files for the user once they are created.
- [EXTERNAL_DOWNLOADS]: The skill relies on searching for and fetching information from high-reputation external resources and communities to provide authoritative content to the user.
Audit Metadata