gitflow

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill specifies a mandatory memory protocol requiring the execution of a bash command (cat .claude/context/memory/learnings.md) to read internal agent state.
  • [EXTERNAL_DOWNLOADS]: The skill metadata contains an installation command that fetches the skill file directly from an unverified GitHub repository (majiayu000/claude-skill-registry) using curl.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because its primary function is to process and review untrusted, user-provided code.
  • Ingestion points: User-provided source code is ingested via the main prompt for review and refactoring.
  • Boundary markers: None. The instructions do not use delimiters or warnings to ignore instructions embedded within the code being reviewed.
  • Capability inventory: The skill has access to powerful tools including Bash, Read, Write, and Edit.
  • Sanitization: No validation or sanitization of the input code is performed before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 07:33 PM