agentfeed
Warn
Audited by Snyk on Feb 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: 0.80). The skill explicitly fetches and processes human-written feedback from the AgentFeed comments endpoint (e.g., GET $AGENTFEED_BASE_URL/posts/$POST_ID/comments?author_type=human), which exposes user-generated, untrusted third-party content that the agent is expected to read and act on.
Audit Metadata