teach
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to open generated HTML lesson files using system CLI commands (e.g., 'open', 'xdg-open'). While intended for user convenience, this involves direct shell command invocation to interact with the local operating system.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external resources listed in 'RESOURCES.md' to generate teaching materials. This creates a surface for indirect prompt injection where instructions embedded in external content could influence the agent's behavior during content generation.
- Ingestion points: 'RESOURCES.md' and the external content (articles, books, websites) it references.
- Boundary markers: Absent; there are no instructions to delimit or ignore embedded instructions within the source material.
- Capability inventory: Ability to write files to multiple directories ('./lessons/', './reference/', './assets/') and execute shell commands to open those files.
- Sanitization: Absent; the skill relies on the agent's synthesis process without explicit validation or escaping of external content.
Audit Metadata