evals-specify

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill and its associated scripts perform local project configuration and file operations. Analysis of the scripts (setup-evals-specify.ps1 and setup-evals-specify.sh) shows they are used to resolve local project paths and environment settings without external network dependencies or sensitive data access.
  • [PROMPT_INJECTION]: The skill processes external failure logs and support tickets to extract criteria, which represents a potential indirect injection surface.
  • Ingestion points: User-provided failure patterns ($ARGUMENTS) and external trace sources (logs/tickets).
  • Boundary markers: None present.
  • Capability inventory: Creates and writes markdown files to the .adlc/drafts/evals/ directory.
  • Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 03:11 PM
Security Audit — agent-trust-hub — evals-specify