legal
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to read and analyze existing user-provided legal documents to identify gaps and conflicts. This represents a potential surface for indirect prompt injection, where malicious instructions could be embedded within the documents being analyzed to influence the agent's drafting behavior.
- Ingestion points: Existing terms, privacy policies, and contracts are read into the agent context (SKILL.md).
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the analyzed documents.
- Capability inventory: The skill is primarily a text-drafting tool and does not define any capabilities for file writing, network operations, or shell command execution.
- Sanitization: No content filtering or validation of the input text is specified.
- [SAFE]: The skill primarily provides informational templates and drafting rules. It does not contain any obfuscated code, remote execution patterns, or attempts to access sensitive system files.
Audit Metadata