The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the podcastindex-pp-cli and podcastindex-pp-mcp binaries from the vendor's GitHub repository and NPM registry using npx and go install.
[COMMAND_EXECUTION]: The skill is primarily a wrapper for executing the podcastindex-pp-cli tool, which performs various operations including API requests and local database management.
[DATA_EXFILTRATION]: The CLI includes a --deliver webhook:<url> parameter that allows the output of any command to be sent to an arbitrary external URL via a POST request. While a documented feature, it provides a direct mechanism for data exfiltration.
[INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted content from the PodcastIndex API, including podcast titles, descriptions, and full-text transcripts which could contain malicious instructions.
Ingestion points: find search, episodes byfeedid, and tgrep commands in SKILL.md ingest external podcast metadata and transcripts.
Boundary markers: No specific delimiters or warnings are provided to the agent to differentiate between podcast content and instructions.
Capability inventory: The skill can execute shell commands (podcastindex-pp-cli), write files (--deliver file:), and make network requests (--deliver webhook:).
Sanitization: There is no evidence of sanitization for the ingested podcast data before it is presented to the agent.

pp-podcastindex