performance-profiler
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted project source code from user-specified paths, which creates a surface where malicious instructions hidden in the code could be processed by the agent.
- Ingestion points: Project files located at
/path/to/projectare read and analyzed by the profiler scripts. - Boundary markers: The instructions lack clear delimiters or specific directives to the agent to disregard instructions found within the project data.
- Capability inventory: The skill utilizes powerful utilities such as
k6,Artillery, andpy-spythat have the capability to perform network operations and system-level inspections. - Sanitization: There is no evidence of sanitization or filtering of the external project content before it is processed.
Audit Metadata