podcast-downloader

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill possesses a surface for indirect prompt injection via runtime data ingestion.
  • Ingestion points: Podcast titles and descriptions fetched from the iTunes API and RSS feeds.
  • Boundary markers: No specific delimiters or instructions are used to treat external metadata as untrusted data.
  • Capability inventory: The skill allows filesystem writing and network downloads.
  • Sanitization: The skill sanitizes filenames to prevent path traversal, but it does not sanitize the text content of the metadata.
  • EXTERNAL_DOWNLOADS (SAFE): The skill fetches audio files and metadata from legitimate Apple Podcast endpoints.
  • COMMAND_EXECUTION (SAFE): The skill uses standard Python script execution and package management (pip) to perform its tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:25 PM