The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content, specifically Amazon customer reviews and market descriptions, which could contain instructions aimed at influencing the agent's behavior.
Ingestion points: Data is retrieved from the Jiimore API via scripts/jiimore_get_niche_info.py and presented to the agent.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat these external text fields as untrusted data.
Capability inventory: The agent can execute local scripts that perform network operations and file writes.
Sanitization: No filtering or sanitization of raw Amazon review text is performed before it enter the agent's context.
[COMMAND_EXECUTION]: The skill relies on the execution of local Python scripts to interact with vendor APIs and manage local data.
Evidence: scripts/jiimore_get_niche_info.py and scripts/onboarding.py are executed to perform market queries and authentication flows.
[DATA_EXFILTRATION]: The skill transmits market query parameters and feedback data to vendor-controlled endpoints.
Evidence: API requests are sent to subdomains of linkfox.com, including tool-gateway.linkfox.com and skill-api.linkfox.com.

linkfox-jiimore-get-niche-info