staleness-audit
Warn
Audited by Snyk on Jun 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s runtime LLM context is fed by scanning the repo’s own pin files (e.g.,
.nvmrc,engines,.tool-versions, CI workflow YAML, DockerFROMtags) and by web-fetched upstream release/EOL data during validation; that web-fetched content is outsider-authored free text that can be ingested into the agent context via the validate step’s fetch/parse path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata