alternative-uses-task-designer
Warn
Audited by Snyk on Jun 21, 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). The skill’s runtime workflow for the “Web Search” (and potentially “ChatGPT”) AI-augmented conditions explicitly allows participants to use external web search/ChatGPT and then submit the resulting free-form ideas, which are outsider-authored text that can be copied into the agent/LLM context via participant responses.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata