adr-review
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are focused on architectural compliance and code review using local repository tools.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute git commands (e.g., git diff). These commands are standard for the skill's purpose and operate on local repository data.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted code and ADR files.
- Ingestion points: reads output from git diff (Step 1) and contents of ADR files in docs/adr/ (Step 3).
- Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore embedded commands in the reviewed files.
- Capability inventory: utilizes Bash (for git/grep), Read, and specialized MCP tools for database and memory queries.
- Sanitization: Absent; content is read and processed directly by the agent.
Audit Metadata