icypeas

Warn

Audited by Snyk on Apr 22, 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). This skill's SKILL.md explicitly lists actions that scrape and ingest public third-party pages (e.g., "Scrape LinkedIn Company" and "Scrape LinkedIn Profile" in the "Popular actions" section, and the Membrane proxy request flow), so the agent will fetch and interpret untrusted web/user-generated content as part of its workflow.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 22, 2026, 01:41 AM
Issues
1