bifrost-platform
Warn
Audited by Snyk on Apr 6, 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 workflow and preflight instructions explicitly direct the agent to inspect and clone remote repositories and to run commands like
bifrost github repos <installation-id>/bifrost github installationsandgit remote -v, which cause the agent to fetch and parse user-generated content from GitHub (public or private third‑party repos) and use that content to make deployment and runtime decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata