user-research-synthesis

Warn

Audited by Snyk on Feb 19, 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.md explicitly instructs the agent to "pull research inputs" from connected tool categories such as ~~user feedback (e.g., Intercom), ~~knowledge base (e.g., Notion), and ~~meeting transcription (e.g., Fireflies) — user-generated, third‑party content the agent is expected to read and use to drive synthesis and decisions, so it can materially influence actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 03:56 PM