harness-audit
Warn
Audited by Snyk on Jul 31, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In
agents/harness-analyzer.md, the runtime inventory pass reads/greps arbitrary repo-authored files (e.g.,CLAUDE.md,.claude/rules/*.md,.claude/settings.json, hooks/commands/skills/agents) to produce the inventory artifact that is then consumed for scoring.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata