w-perf

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads external 'testing docs' to identify performance budgets, which introduces a surface where malicious instructions could be embedded in those documents.
  • Ingestion points: Instructions in SKILL.md mandate reading testing documentation from the repository.
  • Boundary markers: The skill lacks clear delimiters or 'ignore embedded instructions' warnings for the data it processes.
  • Capability inventory: The skill has access to repository profiling tools, test suites, and the gh CLI tool to measure and apply changes.
  • Sanitization: No sanitization or validation mechanisms are defined for the documentation content being ingested.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 01:00 AM
Security Audit — agent-trust-hub — w-perf