code-review-excellence

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest and analyze untrusted external content including code, requirements, and test signals.
  • Ingestion points: Processes 'context, requirements, and test signals' provided during a code review task.
  • Boundary markers: Absent. There are no instructions to delimit external content or to ignore instructions embedded within the code being reviewed.
  • Capability inventory: The skill references a file read operation ('open resources/implementation-playbook.md') but does not contain commands for network access, shell execution, or file writing.
  • Sanitization: Absent. The skill does not instruct the agent to sanitize or escape the input data before processing.
  • [No Executable Code] (INFO): The skill consists entirely of markdown instructions and lacks any executable scripts, shell commands, or dependency manifests, which significantly limits the immediate risk of exploitation.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 17, 2026, 12:04 AM