performant-python
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for analyzing external codebases and architectural documents, creating a vulnerability surface for instructions embedded in data.\n
- Ingestion points: As detailed in ARCHITECTURE_REVIEW_TEMPLATE.md, the skill processes codebases, ADRs, and architecture documents.\n
- Boundary markers: The instructions lack explicit delimitation or warnings to disregard instructions found within the analyzed technical artifacts.\n
- Capability inventory: The skill suggests performing architectural analysis and using tools like Py-Spy, Scalene, and Locust for performance profiling.\n
- Sanitization: No specific filtering or sanitization protocols for external content are defined in the optimization workflow.\n- [COMMAND_EXECUTION]: The skill instructions involve executing command-line utilities for system analysis and testing.\n
- Evidence: SKILL.md directs the agent to use Py-Spy for profiling running processes and Locust or k6 for executing load tests.
Audit Metadata