consensus-review

Warn

Audited by Snyk on Aug 26, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). In references/command.md, the workflow accepts $ARGUMENTS as “a free-text question, proposal, architecture choice, or spec” and embeds that {USER DESCRIPTION, VERBATIM} into the runtime review prompt, so outsider-authored text is directly ingested by the LLM.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 26, 2026, 04:47 AM
Issues
1
Security Audit — snyk — consensus-review