bmad-code-review

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from multiple external sources, creating a potential surface for indirect prompt injection attacks.
  • Ingestion points: The skill reads and processes unified diffs ({diff_file}), ticket descriptions ({ticket_file}), and developer narratives ({claims_file}) in step-01-gather-context.md.
  • Boundary markers: The subagent prompts defined in customize.toml (e.g., for the blind-hunter and quick lenses) lack clear boundary markers or delimiters between the instructions and the untrusted content being reviewed.
  • Capability inventory: The skill has significant capabilities, including executing shell commands (git, gh, uv) and the ability to modify the project's source code by applying patches in step-05-present.md.
  • Sanitization: There is no explicit sanitization of the content before it is passed to subagents. While step-03-triage.md includes a manual verification step for findings, it relies on the agent's judgment to detect malicious intent within the findings.
  • [COMMAND_EXECUTION]: The skill relies on executing shell commands and local project scripts to function.
  • Execution of local scripts: In SKILL.md and step-01-gather-context.md, the skill uses uv run to execute scripts located within the project's own directory structure (_bmad/scripts/render_skill.py and _bmad/method/scripts/tickets.py). This creates a dependency on the integrity of the project being reviewed.
  • VCS Tooling: The skill invokes git and gh (GitHub CLI) to retrieve diffs, logs, and pull request information.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 10:20 PM