deepgram-upgrade-migration
Warn
Audited by Snyk on Mar 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to review external changelogs and migration guides by fetching public URLs (e.g., curl to https://api.github.com/repos/deepgram/deepgram-js-sdk/releases/latest, npm view, and external docs/audio like https://static.deepgram.com/examples/nasa-podcast.wav and developers.deepgram.com), so the agent would ingest public third‑party content that can materially influence upgrade/migration decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata