The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to automatically install the listenhub CLI tool and handle authentication tasks if the binary is not found, explicitly stating the agent should "never ask the user to run commands manually" during this setup.
[COMMAND_EXECUTION]: The interaction flow generates and executes shell commands to manage configuration files and invoke the listenhub CLI with multiple parameters derived from user input.
[INDIRECT_PROMPT_INJECTION]: The skill has a high attack surface as it is designed to ingest arbitrary text and content from remote URLs to be processed into podcast scripts.
Ingestion points: User-provided topic descriptions, URLs, and text blocks in SKILL.md.
Boundary markers: Absent; the skill interpolates untrusted user content directly into CLI command arguments (--query, --source-url, --source-text) without clear delimiters.
Capability inventory: The skill has the ability to execute CLI commands, write to the filesystem, and perform network requests.
Sanitization: No sanitization or filtering logic is present to handle potentially malicious instructions embedded in the source materials.
[EXTERNAL_DOWNLOADS]: The generation workflow uses curl to download audio files from dynamic URLs provided by the CLI service to the user's local directory.

podcast