terms-conditions
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a shell script (
scripts/verify.sh) designed to lint generated Markdown documents. The script uses standard POSIX commands (grep,find,sed) to identify archaic legalese and verify the presence of mandatory structural sections. It does not perform network operations or access sensitive system files. - [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided information about a product's features and target audience to generate customized legal drafts.
- Ingestion points: Product descriptions and feature lists provided in the user prompt.
- Boundary markers: None explicitly defined in the instructions for the agent, though the skill directs the user to perform manual review.
- Capability inventory: The skill drafts text and utilizes a local linter script; it has no network access or file-writing capabilities beyond providing text to the agent.
- Sanitization: None, as the output is intended for human-readable legal drafting.
- [SAFE]: All referenced legal templates and drafting guidelines focus on standard commercial compliance and user protection. The skill explicitly disclaims legal advice and mandates attorney review for all generated content.
Audit Metadata