phoenix-github

Warn

Audited by Snyk on Mar 21, 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 runtime use of the GitHub CLI and GraphQL against the public Arize-ai/phoenix repository (e.g., "gh api repos/Arize-ai/phoenix/issues/{number}" and project GraphQL mutations), meaning the agent will fetch and act on user-generated GitHub issue content which could contain instructions that influence its actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 21, 2026, 11:56 AM
Issues
1