contract-review
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines an ExecutionProxy Interface used to run commands such as npm test through the rtk prefix. This is intended for deterministic verification within a development workflow.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as its primary function is to process and analyze external contract data. 1. Ingestion points: Contract text ingested for review in the Contract Review process. 2. Boundary markers: Explicit delimiters for untrusted data are not provided in the prompt structure. 3. Capability inventory: Includes shell command execution via the ExecutionProxy, file storage via MemoryStore, and MCP tool invocation (sequentialthinking, context7). 4. Sanitization: The instructions include a mandatory protocol to treat external data as hostile and redact PII or secrets before processing.
Audit Metadata