kotler-macro-analyzer

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external data from the web using search tools to perform its analysis. This creates a standard surface for indirect prompt injection where malicious content on a web page could attempt to influence the agent's output.
  • Ingestion points: SKILL.md (Step 1: Real-time Data Retrieval) instructs the agent to gather economic, political, and legal data via search tools.
  • Boundary markers: No explicit instructions are provided to the agent to ignore or delimit potentially malicious instructions found within the retrieved data.
  • Capability inventory: The skill description only implies the use of search capabilities; no file-writing, code execution, or advanced subprocess capabilities are mentioned or requested.
  • Sanitization: No sanitization or validation logic is defined for the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 02:14 AM
Security Audit — agent-trust-hub — kotler-macro-analyzer