matt-teach
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to open generated HTML lesson files locally for the user (SKILL.md).
- [EXTERNAL_DOWNLOADS]: The agent is directed to retrieve information from external web resources and online communities to populate the
RESOURCES.mdfile and build lesson content (SKILL.md, RESOURCES-FORMAT.md). - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection due to its core function of processing untrusted external content into interactive lessons.
- Ingestion points: External high-quality resources and communities identified and logged in
RESOURCES.md(SKILL.md). - Boundary markers: There are no instructions for the agent to use delimiters or ignore embedded instructions when reading these external sources.
- Capability inventory: The agent can write various file types (HTML, Markdown, CSS, JS) and execute CLI commands to open files (SKILL.md).
- Sanitization: The instructions do not define any validation, filtering, or escaping mechanisms for content retrieved from the web before it is used to generate lessons.
Audit Metadata