tutorial
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local Python scripts (init_tutorial.py, build.py, check_tutorial.py) and Rust development tools (cargo, clippy) to initialize, render, and validate tutorials. \n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted implementation plans. \n
- Ingestion points: Implementation plans provided by the user in the repository context. \n
- Boundary markers: No specific delimiters or "ignore" instructions for the plan content are established in the instructions. \n
- Capability inventory: File system writing and shell command execution for build and validation stages. \n
- Sanitization: HTML escaping is implemented in the build.py script to prevent cross-site scripting (XSS) in the final tutorial output. The skill also enforces strict technical prose and forbids the use of slogans or invented branding to mitigate the risk of the agent adopting malicious personas or content.
Audit Metadata