omnicaptions-translate
Fail
Audited by Snyk on Feb 15, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to ask the user for their Gemini API key and to run commands with
-k <key>(and save it to a config file), which requires the LLM to accept and embed the secret verbatim in commands/config — creating an exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly processes external caption files and even lists "Translate YouTube video transcripts" and a related
/omnicaptions:downloadstep, so it will ingest public, user-generated caption content (untrusted third-party data) as part of its workflow.
Audit Metadata