jqschema
Warn
Audited by Snyk on May 9, 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). Flagged because SKILL.md explicitly instructs ingesting public GitHub API search results (e.g., "echo '{}' | gh api search/repositories -f q=... | /tmp/gh-aw/jqschema.sh" and "gh api search/code ... > /tmp/sample.json") — user-generated, untrusted JSON — and the agent reads that schema to decide further queries, so third-party content can materially influence subsequent tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata