skills/jeremylongshore/tons-of-skills-marketplace/windsurf-performance-profiling/Gen Agent Trust Hub
windsurf-performance-profiling
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the AI agent ingests and analyzes external performance data to identify bottlenecks.
- Ingestion points: The agent reads profiling data from JSON files (e.g.,
baseline.profile.json,current.profile.json) located in the project's.windsurf/performance/profiles/directory. - Boundary markers: The skill instructions do not provide specific delimiters or instructions to ignore potential natural language commands embedded within the performance data values.
- Capability inventory: The skill allows access to
Bash,Write, andEdittools, which represents a significant capability set if an injection were successful. - Sanitization: No data validation or sanitization steps are defined for the JSON profiling files before they are processed by the agent.
Audit Metadata