douyin-search

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a Bash script (scripts/douyin_task.sh) to execute curl and jq for API interactions. This is the primary intended behavior and includes thorough validation of user-provided arguments.
  • [EXTERNAL_DOWNLOADS]: The script connects to the Frevana API at ai-factory.frevana.com to search for and retrieve Douyin video metadata. This is the service provider required for the skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: As the skill fetches and returns data from an external social media platform (Douyin), it constitutes a surface for indirect prompt injection if the agent processes the resulting text content.
  • Ingestion points: Data enters via the result action in scripts/douyin_task.sh which fetches JSON results from the Frevana API.
  • Boundary markers: The skill documentation does not define specific delimiters for the search results in the agent's context.
  • Capability inventory: The script allows network requests via curl and file writing via the --output flag.
  • Sanitization: The script uses jq to ensure valid JSON structure for API payloads and results, but does not sanitize the content of the retrieved search items.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 05:29 AM