The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves transcript data from external YouTube videos, which are untrusted sources that could contain instructions designed to influence the AI agent's behavior. Ingestion points: scripts/fetch_transcript.py fetches transcripts from the Apify API and returns them to the agent. Boundary markers: Absent; transcripts are provided as raw text without isolation markers or safety instructions. Capability inventory: The skill utilizes network access via the requests library and local file system access for transcript caching in the .cache/ directory. Sanitization: The skill performs no filtering or sanitization of the transcript content before it enters the agent context.
[EXTERNAL_DOWNLOADS]: The skill connects to api.apify.com to trigger extraction jobs and retrieve results. This is a well-known service and the interaction is standard API usage based on an user-provided token.
[METADATA_POISONING]: There is a discrepancy between the attribution provided in the skill context ('nikiandr') and the metadata in the package.json file ('robbyczgw-cla'). This inconsistency is misleading regarding the skill's origin and maintenance status.

youtube-apify-transcript