comprehensive-unit-testing-with-pytest
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute
cat .claude/context/memory/learnings.mdas part of its mandatory memory protocol to maintain state. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-provided Python test files while possessing powerful tools.
- Ingestion points: The agent reads external files matching the
**/tests/*.pyglob. - Boundary markers: No specific delimiters or 'ignore' instructions are provided to prevent the agent from obeying instructions embedded in the test files.
- Capability inventory: The skill has access to
Bash,Read,Write, andEdittools. - Sanitization: No sanitization or validation of the processed file content is performed.
Audit Metadata