yy-frontend-change-log

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to interact with the local repository. Specifically, it executes git diff --name-only HEAD and git diff --cached --name-only in SKILL.md (Step 2) to identify which files have changed. This is a core part of its intended functionality.
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8) because it ingests untrusted data and has the capability to write to the file system.
  • Ingestion points: The skill reads the content of frontend source files (Vue, React, JS, TS, etc.) identified via git diff or user selection (SKILL.md, Step 2 and Step 3).
  • Boundary markers: Absent. The instructions do not specify any delimiters or safety prompts to prevent the AI from following instructions embedded within the source code files being analyzed.
  • Capability inventory: The skill has the capability to modify files by injecting JSDoc comments at the top (SKILL.md, Step 5).
  • Sanitization: Absent. There is no evidence of sanitization or validation of the code content before it is processed or before the resulting analysis is written back into the file.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 04:04 AM
Security Audit — agent-trust-hub — yy-frontend-change-log