harness-engineering
Warn
Audited by Snyk on May 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly describes the agent analyzing arbitrary GitHub repositories and other external sources (e.g., "we put in a GitHub repo... it's going to analyze that GitHub repo", mentions Hosted Shell network access, Slack/Linear/Calendar integrations and web links), meaning the agent will fetch and interpret untrusted, user-generated third‑party content that can change its actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata