The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script linkfox.py to communicate with the service API. It also provides templates for the agent to generate and execute Python code within sub-agents for data handling tasks, such as merging and processing CSV results. These operations are necessary for the skill's intended analytical purpose.
[EXTERNAL_DOWNLOADS]: The skill makes network requests to agent-api.linkfox.com to submit e-commerce research tasks and retrieve structured results. This network activity is fundamental to its operation as a market research tool.
[DATA_EXFILTRATION]: E-commerce research queries and results are transmitted between the agent and the LinkFox API. This transmission is transparently documented as the primary function of the skill.
[PROMPT_INJECTION]: The skill ingests data from external sources like product reviews and search results, which constitutes an indirect prompt injection surface. Ingestion points: External data from Amazon, TikTok, and 1688 platforms (as described in references/amazon-frontend.md and references/tiktok.md). Boundary markers: No explicit delimiters or warnings are used in the prompt templates. Capability inventory: API interaction and local file system access (writing CSV and JSON files). Sanitization: No specific filtering or escaping mechanisms are described. The risk is assessed as low due to the skill's focus on structured data analysis.

linkfoxagent