do-teach-me
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to 'open the lesson file for the user by running a CLI command'. This involves executing shell commands to interact with the local operating system to launch a browser or file viewer for the generated HTML lessons.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize information from external, high-quality resources to populate
RESOURCES.mdand generate lesson content. This creates a surface for indirect prompt injection if the external sources contain malicious instructions designed to influence the agent's behavior during content generation. - Ingestion points: External URLs, primary sources, and community platforms cited and read by the agent to acquire 'Knowledge' and 'Wisdom' as described in
SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing content from
RESOURCES.mdor external sites. - Capability inventory: The agent has the capability to write files (HTML, Markdown) to the local workspace and execute CLI commands to open these files.
- Sanitization: No specific sanitization or filtering logic is prescribed for the external data before it is interpolated into the generated lessons or learning records.
Audit Metadata