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
bashcommand (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) usingcurl. - [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, andEdit. - Sanitization: No validation or sanitization of the input code is performed before analysis.
Audit Metadata