geo-audit

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze 'raw answers' from various generative AI engines (Doubao, Qwen, Yuanbao, DeepSeek). This untrusted data represents an attack surface where malicious instructions could be embedded to subvert the agent's auditing logic.
  • Ingestion points: The 'Raw answers' input requirement in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious content within the analyzed answers.
  • Capability inventory: The skill instructions focus on text analysis and report generation. No hazardous capabilities such as network access, file writing, or command execution are present in the provided skill files.
  • Sanitization: There are no explicit sanitization or filtering steps for the ingested AI answers before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 01:56 AM