The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Douyin video links, which could contain malicious instructions designed to influence the agent's analysis or subsequent actions.
Ingestion points: The link parameter in scripts/run.py accepts external URLs pointing to Douyin content for analysis.
Boundary markers: None are present; there are no specific delimiters or instructions defined to isolate the external content from the agent's internal logic.
Capability inventory: The skill includes network request capabilities (urllib.request) to communicate with the ai-skills.ai backend.
Sanitization: There is no evidence of sanitization or filtering of the external video content or comments within the provided scripts before processing.

douyin-sentiment-dashboard