change-review
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard version control and development tools, including
git,gh(GitHub CLI), and therepowiseCLI. These tools are used to retrieve diffs, check status, and calculate risk scores within the user's repository environment. The operations are consistent with the skill's stated purpose of change review. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code changes (git diffs and pull requests), which presents a potential surface for indirect prompt injection via malicious code comments or file content.
- Ingestion points: Diff data and file content retrieved via
git diff,gh pr diff, and MCP tools likeget_change_risk(SKILL.md). - Boundary markers: No specific delimiters or instructions to ignore embedded commands within the ingested data are defined.
- Capability inventory: The agent has access to repository file content and various code analysis capabilities including risk assessment, health checks, and architectural decision lookup.
- Sanitization: No explicit filtering or sanitization of the diff content is provided in the instructions.
Audit Metadata