tutorial-checker
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands such as 'psql' and 'python' to validate tutorial code and database setups.
- [EXTERNAL_DOWNLOADS]: The skill uses 'uv pip install' to download and install Python packages defined in a requirements.txt file within the tutorial folder, fetching code from external registries.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external tutorial content (README.md, scripts) without explicit boundary markers or sanitization, and has the capability to execute commands based on that content.
- Ingestion points: Reads local README.md and script files within the tutorial folder.
- Boundary markers: None present to distinguish untrusted content from system instructions.
- Capability inventory: Shell execution (psql, python, uv) on local files.
- Sanitization: No validation of the ingested content before command execution.
Audit Metadata