scope-check
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes dynamic context injection to execute a git command (
git diff --stat HEAD~20) when the skill is loaded. This is used to gather context about recent changes in the repository. This is a standard development workflow operation, and the command is static, minimizing risk. - [PROMPT_INJECTION]: The skill processes data from documentation directories and the codebase, which constitutes an indirect prompt injection surface. While the capability is intended for the skill's primary purpose of scope analysis, the following factors are noted:
- Ingestion points:
design/gdd/,production/sprints/,production/milestones/, and general codebase files. - Boundary markers: Not explicitly defined in the instructions.
- Capability inventory: The skill is limited to reading and searching files (
Read,Glob,Grep) without network exfiltration or destructive capabilities. - Sanitization: No specific filtering of external content is defined.
Audit Metadata