review
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes several git commands (
git diff,git log,git rev-parse) to gather context for the review. These are standard operations for a repository review tool. - [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8).
- Ingestion points: The skill ingests untrusted data from
git diffoutputs,git logcommit messages, and external spec/issue content fetched via the workflow indocs/agents/issue-tracker.md. - Boundary markers: The prompts provided to the 'Standards' and 'Spec' sub-agents do not employ delimiters or explicit instructions to ignore potentially malicious commands embedded within the diffs or issue descriptions.
- Capability inventory: The skill executes shell commands via the git CLI and has the capability to spawn additional general-purpose sub-agents.
- Sanitization: There is no evidence of sanitization, filtering, or escaping of the external data before it is interpolated into the sub-agent prompts.
Audit Metadata