The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the google-api-python-client package. This is a well-known, official library provided by Google for interacting with their APIs and is considered safe.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (YouTube video titles, descriptions, and tags) and uses this data to generate a strategy report. This creates a surface where an attacker could embed malicious instructions in video metadata to influence the agent's behavior during report generation.
Ingestion points: scripts/analyze_strategy.py fetches content from the YouTube Data API v3 (videos, playlists, search results) which is then read by the agent to produce the final Markdown report.
Boundary markers: The instructions do not specify strict delimiters or explicit warnings to ignore embedded instructions within the ingested YouTube data.
Capability inventory: The skill executes a local Python script and performs file system write operations to save the report and data.
Sanitization: The script extracts specific metrics and text but does not perform content sanitization or filtering to prevent instruction injection from the video metadata.

youtube-content-strategist