The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the podscan-pp-cli binary using npx from the @mvanhorn/printing-press package or via go install from the author's GitHub repository.
[COMMAND_EXECUTION]: The skill executes the podscan-pp-cli tool to manage alerts, search episodes, and interact with the Podscan API.
[DATA_EXFILTRATION]: The tool includes an output delivery feature (--deliver webhook:<url>) that can transmit command results to external webhooks. This is a functional capability of the CLI that could be used to send data to remote servers.
[PROMPT_INJECTION]: The skill provides access to untrusted content from podcast transcripts, presenting an indirect prompt injection surface.
Ingestion points: Podcast transcripts and metadata are retrieved via podscan-pp-cli episodes search and podscan-pp-cli podcasts search commands.
Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the podcast data.
Capability inventory: The agent can write to local files and send data to webhooks using the CLI's --deliver flag, which are powerful capabilities if triggered by malicious transcript content.
Sanitization: There is no evidence of sanitization or filtering of external content before it is processed by the agent.

pp-podscan