pr-report

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill follows a standard analytical workflow for reviewing code contributions and does not include any executable scripts or dangerous commands.
  • [EXTERNAL_DOWNLOADS]: The HTML report template references Google Fonts from trusted domains (fonts.googleapis.com and fonts.gstatic.com).
  • [PROMPT_INJECTION]: This skill possesses an indirect prompt injection surface as it processes external, untrusted PR content.
  • Ingestion points: Pull request descriptions, design docs, and repository code (SKILL.md).
  • Boundary markers: The workflow lacks explicit instruction to use delimiters for untrusted input.
  • Capability inventory: The skill is authorized to write report files to local directories (SKILL.md).
  • Sanitization: Step 8 mandates checking for the absence of user-defined forbidden strings in the final artifact.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 07:58 AM