macro-policy-analysis

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists entirely of Markdown-based instructions and metadata. It does not include any Python scripts, Node.js code, shell scripts, or other executable binaries.
  • [PROMPT_INJECTION]: The skill utilizes external data sources, including web_search and the gildata-aidata tool suite (e.g., MacroNewslist, NewsInfoList), to fetch news and policy updates. This constitutes an indirect prompt injection surface where instructions hidden in external web content could potentially influence the agent's output.
  • Ingestion points: Data retrieved through web_search and various gildata-aidata tools (vendor resources) mentioned in the 'Execution Flow' section of SKILL.md.
  • Boundary markers: There are no explicit delimiters or protective instructions provided to the agent to treat external content as untrusted data.
  • Capability inventory: The skill has no capabilities for file system modification, network exfiltration, or code execution.
  • Sanitization: No sanitization or validation mechanisms are implemented for the fetched data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 06:41 AM
Security Audit — agent-trust-hub — macro-policy-analysis