podchaser
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
bash -cto executecurlandjqfor performing GraphQL requests and parsing the results. - [DATA_EXFILTRATION]: The skill stores generated API access tokens in
/tmp/podchaser_token.txtand request payloads in/tmp/podchaser_request.json. Storing sensitive tokens in world-writable directories like/tmpis a common but sub-optimal security practice. - [PROMPT_INJECTION]: The skill retrieves and processes podcast titles, descriptions, and creator bios from
api.podchaser.com, which serves as a vector for indirect prompt injection attacks. - Ingestion points: Metadata returned from GraphQL queries to the Podchaser API (SKILL.md).
- Boundary markers: None identified in the prompt templates.
- Capability inventory: Execution of bash commands for network requests and file operations.
- Sanitization: No explicit sanitization or filtering of API response data is performed before processing.
Audit Metadata