pr-comments
Warn
Audited by Snyk on Feb 16, 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 fetches user-generated PR and issue comments from GitHub using gh api (see scripts/export.sh and scripts/export-all.sh) and then preprocess.sh injects those comment bodies into task prompts that the agent is instructed to read and act on, exposing the agent to untrusted third-party content.
Audit Metadata