The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external TikTok influencer profiles and videos through the Qinghu AI API. This content could potentially contain hidden instructions intended to manipulate the agent's behavior. \n- Ingestion points: Influencer details, video descriptions, and product lists from iqinghu.com (SKILL.md).\n- Capability inventory: The skill uses network tools (curl, fetch) and mentions data export functions (SKILL.md).\n- Boundary markers: The skill does not provide explicit delimiters or instructions to ignore commands embedded within the external influencer data.\n- Sanitization: No data sanitization or validation logic is specified for the influencer-provided text content.\n- [COMMAND_EXECUTION]: The skill instructions advise the agent to use command-line tools such as curl to interact with the API endpoints.\n- [DATA_EXFILTRATION]: The skill transmits user-provided API credentials to the iqinghu.com domain. While this is the intended purpose of the skill, it represents a pattern of transmitting sensitive secrets to a remote service.

qinghu-tiktok-influencer