effect-stream
Warn
Audited by Snyk on May 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly shows workflows that ingest and decode external/untrusted streams (e.g., Stream.paginate for paginated APIs, Stream.fromReadableStream that uses response.body, and NDJSON/Msgpack decoding of raw streams/TCP sockets/files) which the agent is expected to read and can drive downstream actions, so third-party content could influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata