deep-review
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download missing dependencies from the author's repository (
github.com/mikeng-io/agent-skills) usinggit cloneif they are not present locally.\n- [COMMAND_EXECUTION]: UtilizesBashfor repository management (git), directory navigation (ls), and creating output folders (mkdir). It also references theqmdCLI for optional artifact management.\n- [PROMPT_INJECTION]: The skill processes user-provided content and artifacts which are interpolated into reviewer agent prompts, creating an indirect prompt injection surface.\n - Ingestion points: User artifacts and conversation history identified in the
working_scope.\n - Boundary markers: Prompts use markdown headers (e.g.,
## Context to Review) to isolate user content.\n - Capability inventory: Capabilities include writing files (
Write), shell execution (Bash), and sub-task spawning (Task).\n - Sanitization: No explicit sanitization or escaping of interpolated content is implemented beyond standard agent guardrails.
Audit Metadata