perigon

Warn

Audited by Snyk on Apr 30, 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 SKILL.md instructs the agent to connect to Perigon via the Membrane CLI and to run actions like membrane action list and membrane action run to retrieve Article/Search results from Perigon (an external news aggregator/public web source), so the agent will ingest and act on third-party public content that could contain instructions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 30, 2026, 03:19 AM
Issues
1
Security Audit — snyk — perigon