performance-profiler

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute several local shell commands for performance analysis, including python3 scripts/performance_profiler.py, py-spy, go tool pprof, and k6. These commands are standard for the skill's stated purpose of performance engineering and profiling.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it processes untrusted external data.
  • Ingestion points: Project source files located at the path provided to the profiler, and database outputs such as EXPLAIN ANALYZE results or slow query logs.
  • Boundary markers: None identified. The skill does not specify delimiters or warnings to ignore instructions embedded within the files being analyzed.
  • Capability inventory: The skill has the capability to execute shell commands (via python3, py-spy, etc.) and perform database queries.
  • Sanitization: No evidence of sanitization or validation of the content of the project files or log data before processing or interpolation into prompts was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — performance-profiler