china-contract-review

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, such as hardcoded credentials, data exfiltration, or obfuscation, were found within the skill files.- [EXTERNAL_DOWNLOADS]: The skill specifies 'python-docx' as a dependency. This is a standard and reputable library for processing Word documents, which is consistent with the skill's functionality.- [PROMPT_INJECTION]: The skill ingests and processes untrusted legal documents, creating an attack surface for indirect prompt injection.
  • Ingestion points: External contract content and Word documents provided by the user (SKILL.md).
  • Boundary markers: Absent. The prompt does not define specific delimiters to distinguish contract text from analysis instructions.
  • Capability inventory: Document reading and text analysis logic across the skill's workflow.
  • Sanitization: Absent. There are no instructions for sanitizing or escaping the content of the processed contracts.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 04:48 PM
Security Audit — agent-trust-hub — china-contract-review