Skills
Navigate
skills/linkfox-ai/linkfox-skills/linkfox-jiimore-get-niche-info-by-keyword/Gen Agent Trust Hub

linkfox-jiimore-get-niche-info-by-keyword

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local Python scripts (scripts/jiimore_get_niche_info_by_keyword.py and scripts/onboarding.py) to interface with the Jiimore API and handle user account setup tasks.
  • [EXTERNAL_DOWNLOADS]: The onboarding.py script identifies a dependency on the qrcode, pillow, and requests Python packages, which are required for generating payment QR codes and managing network sessions.
  • [DATA_EXFILTRATION]: Market research keywords and session authentication tokens are transmitted to official vendor domains (tool-gateway.linkfox.com, api.linkfox.com, and agent-api.linkfox.com). This behavior is consistent with the skill's primary function.
  • [CREDENTIALS_UNSAFE]: The skill manages authentication via the LINKFOX_AGENT_API_KEY environment variable. A static, base64-encoded application identifier is present in scripts/onboarding.py to facilitate API requests, which does not represent a sensitive user credential.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external market data from API responses and provides it to the agent. While this constitutes a potential attack surface for indirect prompt injection, no active vulnerabilities were detected in the parsing logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:02 AM
Security Audit — agent-trust-hub — linkfox-jiimore-get-niche-info-by-keyword