track-tariff-trends
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains defensive instructions in the 'Content safety' section. It explicitly directs the agent to treat API response fields as data rather than instructions and to ignore any directive-like text (such as 'ignore previous instructions') found in the response. This is a security best practice to mitigate indirect prompt injection risks.
- [DATA_EXFILTRATION]: The skill facilitates communication with 'api.worldmonitor.app' to fetch tariff trends. This is the primary intended function of the skill and does not constitute unauthorized data exfiltration. No access to sensitive local files or credentials was detected.
- [CREDENTIALS_UNSAFE]: The skill uses a placeholder header 'X-WorldMonitor-Key' and an environment variable '$WM_API_KEY' for authentication. No hardcoded secrets or sensitive keys are present in the code.
- [COMMAND_EXECUTION]: A 'curl' command is provided as a usage example. This is for documentation purposes and does not represent an automated or malicious execution pattern.
Audit Metadata