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 HEADandgit diff --cached --name-onlyinSKILL.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