tweetclaw-source-research
Warn
Audited by Snyk on Sep 8, 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 search tweets, replies, and public user context from X/Twitter, which allows outsiders to submit free text that the agent ingests.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata