outgoing-link-audit
Warn
Audited by Snyk on Jul 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow runs
scripts/check_external_links.sh, which fetches third-party URLs at runtime and then ingests their fetched page content/metadata into the agent’s LLM context for classification/reporting, creating an outsider-authored free-text injection path via public web content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata