Legal Compliance Checker
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes workflows for processing untrusted external data, such as contract text and company-specific compliance information, which introduces a surface for indirect prompt injection.
- Ingestion points: Data enters the agent's context through parameters described in the
ContractReviewSystemandPrivacyPolicyGeneratorlogic inSKILL.md. - Boundary markers: The skill does not specify the use of delimiters or instructions to ignore embedded commands within the analyzed documents.
- Capability inventory: No dangerous capabilities, such as file system modification, network exfiltration, or shell command execution, are requested or used by the skill.
- Sanitization: No input sanitization or validation logic is present in the provided templates.
- [SAFE]: Comprehensive analysis of the instructions and code templates revealed no evidence of malicious intent, obfuscation, or unauthorized credential access.
Audit Metadata