reviewer-tests
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes standard development tools including
git diffto analyze code changes andbd showto retrieve task metadata from a task management system. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from external sources.
- Ingestion points: Reads task descriptions, acceptance criteria, and pull request content from the
beadsissue tracker and the local filesystem. - Boundary markers: Missing explicit delimiters or instructions for the agent to ignore embedded commands within the ingested task descriptions or PR body content.
- Capability inventory: The skill has the ability to create new blocking issues and execute local shell commands (
git,bd). - Sanitization: No validation or sanitization of input from the task management system is described in the review process.
Audit Metadata