team-code-review
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from the repository and external agent reports, using this data to steer the behavior of an 'implementer' agent.
- Ingestion points: The skill reads
1-task.md,8-plan.md, and the output reports from thecode-reviewer,technical-writer,ux-reviewer, andverifieragents. - Boundary markers: No explicit delimiters or instruction-ignore warnings are specified for the payload sent to the implementer agent.
- Capability inventory: The skill executes
gitcommands, local shell/Node.js scripts, and performs file system writes for review records and theTodoWriteledger. - Sanitization: Reviewer findings are aggregated, joined by spaces, and relayed to the implementer without escaping or sanitization of potential injection content.
- [COMMAND_EXECUTION]: The skill relies on the execution of several internal scripts and git commands to analyze the environment and manage the review state.
- Executes
scripts/change-profile.mjsvianodeto determine review depth based on git diff metrics. - Executes
scripts/tree-check.shanddiscover-topic.shvia the shell to monitor worktree integrity and resolve artifact paths. - Frequently invokes
gitwith the-Cparameter to perform status, diff, and rev-parse operations across various worktrees.
Audit Metadata