yy-create-report
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill dynamically constructs a shell command using data retrieved from the local Git configuration.
- Evidence: The instructions in
SKILL.mdspecify fetchinguser.nameand using it as a parameter ingit log --author="用户名". If the local Git configuration contains shell metacharacters, it could lead to command injection during execution. - [PROMPT_INJECTION]: The skill processes untrusted commit message data, creating a surface for indirect prompt injection.
- Ingestion points: Commit messages retrieved via
git loginSKILL.md. - Boundary markers: Absent; the agent is instructed to categorize and list commit messages directly without delimiters or safety instructions.
- Capability inventory: Subprocess execution of
gitcommands. - Sanitization: Absent; the skill does not include instructions to validate or escape commit message content before analysis.
Audit Metadata