opengrep
Warn
Audited by Snyk on Feb 19, 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 cloning and loading public community rule repositories (e.g., "git clone https://github.com/opengrep/opengrep-rules.git" and running "opengrep scan -f opengrep-rules/ ."), so the agent will ingest and act on untrusted, user-generated rule content from GitHub which can materially influence scanning behavior.
Audit Metadata