upwork-invitation-responder
Warn
Audited by Snyk on Jul 23, 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). This skill’s runtime workflow ingests the operating user-pasted “invitation” text (outsider-authored free text from a client) directly as an input, which the agent would then place into LLM context for generating the reply.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata