exploring-replay-vision-observations
Warn
Audited by Snyk on Sep 10, 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). The skill instructs the agent to pull session recording observations and LLM-generated probe findings from Replay Vision, which can be staged by anyone holding the project token, representing untrusted outsider-authored text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata