The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes YouTube comments, which are untrusted external data sources that could contain malicious instructions intended to manipulate the agent's behavior.
Ingestion points: External data enters the agent context through the result_string returned by the run_youtube_comments_task function in scripts/youtube_comments_api.py.
Boundary markers: The skill lacks explicit delimiters or warnings to the agent to ignore potentially malicious instructions embedded within the extracted YouTube comment text.
Capability inventory: The skill has the capability to perform network operations (communicating with the BrowserAct API) and access the BROWSERACT_API_KEY from the environment.
Sanitization: There is no evidence of sanitization, filtering, or escaping applied to the comment_text field before it is presented to the agent for analysis or summarization.

youtube-comments-api-skill