profilesmash
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository being audited, including source code, benchmarks, and configuration files. * Ingestion points: Repository content is read during the survey and cataloging phases (SKILL.md, sections 1 and 2). * Boundary markers: No explicit boundary markers or 'ignore' instructions are specified for processing these files. * Capability inventory: The agent is authorized to build and run code locally (SKILL.md introduction). * Sanitization: The skill does not specify sanitization or validation of the files it reads before processing or execution.
- [DYNAMIC_EXECUTION]: The skill instructions explicitly allow the agent to build the project and execute local benchmarks and profilers (SKILL.md introduction). While this is intended for performance auditing, it involves executing code from the repository environment.
Audit Metadata