run-tests
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill constructs shell commands using user-provided input. Specifically, the
{name}argument is interpolated directly into the commanduv run pytest clients/{name}/tests/ -v(SKILL.md). If the agent does not sanitize this input, it could lead to command injection. - [PROMPT_INJECTION]: There is a risk of indirect prompt injection due to how external data is handled.
- Ingestion points: The agent reads and summarizes output from
pytest, including potentially attacker-influenced assertion messages (SKILL.md). - Boundary markers: No delimiters or explicit instructions to ignore embedded text are used when processing the test output.
- Capability inventory: The skill allows shell command execution via
uv(SKILL.md). - Sanitization: There is no evidence of sanitization or filtering applied to the test output before it is summarized.
Audit Metadata