podchaser
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 users/agents to insert raw Client ID and Client Secret into request JSON and curl commands (replace /), which requires the LLM to handle and potentially output secret values verbatim, 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 directly queries the public Podchaser GraphQL API (https://api.podchaser.com/graphql) to retrieve podcast metadata, episode transcripts, descriptions and creator/host bios — all public/user-generated content that the agent would ingest and could carry indirect prompt injection.
Audit Metadata