limitation-of-liability-general

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Indirect Prompt Injection] (SAFE): The skill is designed to process untrusted data (user-provided contracts), creating a potential surface for indirect prompt injection.
  • Ingestion points: Contract text uploaded or pasted by the user as described in SKILL.md.
  • Boundary markers: Absent; the instructions do not define specific delimiters to separate user content from system instructions.
  • Capability inventory: None; the skill does not include any scripts, shell commands, file system writes, or network operations.
  • Sanitization: Not applicable as the skill performs no programmatic execution or external data transmission.
  • [General Security] (SAFE): No obfuscation, hardcoded credentials, or persistence mechanisms were found. The skill references a local markdown file (scripts/playbook.md) for guidance but does not execute any logic contained therein.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 11:46 AM
Security Audit — agent-trust-hub — limitation-of-liability-general