The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill connects to https://tool-gateway.linkfox.com to retrieve market data and https://skill-api.linkfox.com for feedback reporting. These are official vendor endpoints for 'linkfox-ai' and are used as intended for the skill's primary function.
[CREDENTIALS_UNSAFE]: Authentication is handled correctly via the LINKFOXAGENT_API_KEY environment variable. The skill provides clear instructions for users to set this variable themselves, avoiding hardcoded secrets.
[COMMAND_EXECUTION]: The Python script jiimore_get_niche_info.py uses standard libraries (urllib, json) to perform its tasks and does not involve arbitrary command execution or shell spawning.
[DATA_EXPOSURE]: While the skill retrieves external data, it does not access sensitive local files (such as SSH keys or AWS credentials) or exfiltrate private user information.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external API (jiimore/getNicheInfo) and presents it to the user.
Ingestion points: Data enters the agent context from the JSON response of the Jiimore API, specifically fields like nicheTitle and positiveCustomerReviewInsights.
Boundary markers: None explicitly defined in the instructions to separate API data from instructions.
Capability inventory: The skill is limited to displaying structured data and images in the chat interface.
Sanitization: The Python script parses the response as JSON but does not perform content sanitization. However, given the structured nature of the data and limited capabilities, the risk is minimal.

linkfox-jiimore-niche-info