pr

Pass

Audited by Gen Agent Trust Hub on Oct 13, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists exclusively of markdown instructions, text templates, and descriptive metadata. It does not include any logic that executes shell commands, performs network requests, or accesses sensitive system files.
  • [NO_CODE]: The repository contains only a markdown definition file (SKILL.md) and does not bundle any scripts, binaries, or source code files for execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data like build logs, test results, and a glossary file (CONTEXT.md). Although this defines an ingestion surface for untrusted data, the skill's restricted capability (generating a Pull Request body text) and lack of privileged operations render this surface safe. Evidence: Ingestion points are the verify protocol output and glossary; Boundary markers are not specified; Capabilities are limited to text generation; Sanitization is not mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 13, 2026, 03:22 AM