durable-task-java
Warn
Audited by Snyk on Mar 2, 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's documentation and required workflow (SKILL.md → "HTTP Calls and I/O" example) instructs implementing an activity like "FetchData" that performs HttpClient requests to a provided URL (i.e., arbitrary external web pages), so the agent can ingest and act on untrusted third-party web content returned by those calls.
Audit Metadata