changelog-scan
Warn
Audited by Snyk on Jun 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Outsider free text is ingested via the skill’s WebFetch steps that fetch public Codex documentation pages (e.g.,
code.codex.com/docs/en/changelog.md,llms.txt, hooks/plugins/cli refs) and then parse/extract their prose into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata