coverage

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting and processing untrusted data from local project files. \n
  • Ingestion points: SKILL.md (utilizes Read, Grep, and Glob tools to ingest file or module content). \n
  • Boundary markers: Absent; the instructions do not specify delimiters or provide warnings for the agent to ignore instructions embedded within the analyzed content. \n
  • Capability inventory: SKILL.md (executes shell commands via Bash(npm test:*) and suggests further tool-mediated actions like /tdd, /checkin, or /refactor). \n
  • Sanitization: Absent; no evidence of content validation or escaping before interpolation into the AI context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 09:14 PM
Security Audit — agent-trust-hub — coverage