The Agent Skills Directory

[DATA_EXFILTRATION]: The skill performs network operations to an external domain (ai-factory.frevana.com) to fetch Douyin data.
Evidence: The script scripts/douyin_task.sh uses curl to send GET and POST requests to the API base URL.
Context: The skill sends a FREVANA_TOKEN (provided via environment variable or command argument) in the Authorization header to authenticate these requests.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Douyin boards and trending topics which could contain adversarial instructions.
Ingestion points: Data enters the agent context through the JSON response from the Frevana API in scripts/douyin_task.sh.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic; the agent is instructed to return the JSON result "unchanged".
Capability inventory: The skill possesses network communication capabilities (curl) and file system write access (./out/).
Sanitization: The skill does not perform sanitization or filtering of the fetched content before presenting it to the agent.
[COMMAND_EXECUTION]: The skill executes shell commands to perform its core logic.
Evidence: The douyin_task.sh script invokes curl, jq, uuidgen, and openssl via the system shell.

douyin-hot-search