contract-review

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes external, potentially untrusted documents (contracts). A malicious contract could contain hidden instructions to manipulate the AI's review logic or redlining suggestions.
  • Ingestion points: The skill reads contract text and organization playbooks provided by the user.
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the contract text.
  • Capability inventory: The skill generates analysis and redlines but lacks capabilities for file modification, network access, or command execution.
  • Sanitization: No methods for filtering or sanitizing instructions from the input text are mentioned.
  • [NO_CODE]: The skill consists entirely of markdown instructions and metadata. It does not include any scripts, executables, or third-party code dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 08:21 PM