podchaser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs replacing placeholders with the Client ID and Client Secret in a request JSON (and writing that JSON to disk for curl), which requires embedding secret values verbatim into generated commands/files and therefore exposes secrets to the agent/output.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill makes GraphQL requests to Podchaser's public API (https://api.podchaser.com) to retrieve podcast metadata, episode descriptions and transcripts—user-generated/untrusted content that the agent is expected to read and could materially influence its subsequent responses or actions.