legal-auto-signer

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it parses and acts upon data from untrusted external sources like legal contracts.
  • Ingestion points: The skill uses extraction tools to parse PDF or Word contracts into text for analysis (SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions to treat the contract content strictly as data, leaving the agent vulnerable to instructions hidden within the document text.
  • Capability inventory: The skill can interface with e-signature APIs (DocuSign, HelloSign) to sign or approve documents based on its analysis (SKILL.md).
  • Sanitization: No evidence of sanitization, filtering, or validation is present to neutralize potential malicious instructions embedded in the processed contracts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 05:56 PM
Security Audit — agent-trust-hub — legal-auto-signer