constraint-debug

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill functions as a simple redirect to the phx:ecto-constraint-debug tool.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user data ($ARGUMENTS) into instructions without delimiters or sanitization. In the specific context of a tool alias, this pattern is evaluated as safe.
  • Ingestion points: $ARGUMENTS in SKILL.md.
  • Boundary markers: Not present.
  • Capability inventory: Tool invocation of phx:ecto-constraint-debug.
  • Sanitization: None.
  • [DATA_EXPOSURE]: No sensitive data access or hardcoded credentials were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:40 AM
Security Audit — agent-trust-hub — constraint-debug