compare-macro-history
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or behaviors were identified in the skill. The instructions and structure are consistent with the stated purpose of retrieving macro-economic data.
- [INDIRECT_PROMPT_INJECTION]: The skill addresses potential indirect prompt injection risks in its 'Content safety' section. It instructs the agent to treat all response labels and text as data rather than instructions, and to explicitly ignore any directive-like content found within responses from the external API.
- [CREDENTIALS_UNSAFE]: The skill provides an example API key (
wm_0123456789abcdef0123456789abcdef01234567) solely to demonstrate the required header format. This is a generic placeholder and does not represent a leaked or valid credential. - [EXTERNAL_DOWNLOADS]: The skill makes legitimate network requests to
worldmonitor.appto fetch economic datasets. This functionality is essential for the skill's primary purpose and uses standard REST and MCP communication patterns.
Audit Metadata