The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from an external file to influence its behavior and recommendations.
Ingestion points: The skill reads .agents/youtube-context.md at startup to gather channel-specific information.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the contents of the context file as potentially untrusted data.
Capability inventory: The skill primarily performs text analysis and strategic planning; no dangerous capabilities such as network access, file writing, or command execution were identified in the provided file.
Sanitization: The skill does not implement validation or sanitization of the content read from the context file.

channel-strategy