ia-reflect
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md’s required workflow includes “Scan the full conversation” and “For each review comment received” (inbound PR/MR review), which can include outsider-authored free text from other participants’ messages/comments that the agent reads and then uses for reflection and memory capture.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata