cx-scope
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (LOW): The skill executes local shell commands (git, jq, mkdir) to manage project directories and read configurations. While variables are quoted, it constitutes a local command execution surface.- PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection (Category 8). Ingestion points: User-supplied feature names and output from a code exploration subagent. Boundary markers: Missing markers to delimit untrusted data in templates. Capability inventory: File system writes, directory creation, and GitHub API interactions. Sanitization: Mentions slugification for feature names, which limits path traversal risks.
Audit Metadata