reviewer-architecture

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from the codebase and issue tracker.
  • Ingestion points: The agent reads the full codebase context, surrounding packages, reference directories, and external issues using bd list/show (SKILL.md).
  • Boundary markers: The instructions lack specific delimiters or instructions to ignore potential commands embedded within the code being analyzed.
  • Capability inventory: The skill possesses file-reading capabilities, executes git commands, and can create new issues via the bd tool.
  • Sanitization: There is no logic for sanitizing or escaping the content retrieved from the repository or issue tracker.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to perform code analysis and interact with the project's issue system.
  • Evidence: Executes git diff and bd (beads) CLI tool commands (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:38 PM
Security Audit — agent-trust-hub — reviewer-architecture