recon
Warn
Audited by Snyk on Jul 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Risk comes from the
recon issuerequired workflow reading outsider-authored GitHub issue body/comments viagh issue view <number> --json ... body ... comments ..., which injects that free text into the agent’s LLM context for planning.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata