yy-frontend-commit
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple Git commands (
git status,git diff,git add,git commit) to analyze project state and perform version control operations. While these are necessary for its primary purpose, they involve direct shell interaction. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and analyzes file content via
git diffandgit diff --staged. Malicious instructions embedded in comments or strings within the code being analyzed could influence the agent's summary or behavior. - Ingestion points: Project file contents accessed through
git diffcommands. - Boundary markers: Absent. The instructions do not specify a delimiter or a directive to ignore instructions found within the code changes.
- Capability inventory: Shell command execution via the Git CLI, including
git addandgit commit. - Sanitization: Absent. The skill does not sanitize the output of the diff commands before processing them as natural language context.
Audit Metadata