contract-redline
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions for an AI agent and does not contain any scripts, binaries, or command executions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze commercial contracts, which are untrusted external inputs. This creates a surface for indirect prompt injection if a contract contains hidden instructions meant to subvert the review process. 1. Ingestion points: The agent is instructed to read and analyze contract text provided as input in SKILL.md. 2. Boundary markers: No specific delimiters or warnings are defined to separate contract text from core instructions. 3. Capability inventory: No executable capabilities (subprocess, network access, or file-write) are included in the skill. 4. Sanitization: The skill does not describe any methods for sanitizing or filtering input contract text.
Audit Metadata