agents-md-creator
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill contains various terminal commands such as
pnpm install,pip install, andgo mod download. However, these are provided exclusively as text templates for inclusion in a markdown file. The skill itself does not invoke these commands. - [EXTERNAL_DOWNLOADS] (SAFE): The templates reference standard package managers (pnpm, pip, go) and testing frameworks. There are no links to untrusted third-party scripts or remote code execution patterns.
- [DATA_EXFILTRATION] (SAFE): No file system access or network communication patterns were detected. The skill only facilitates the creation of project-level documentation.
- [PROMPT_INJECTION] (SAFE): The skill contains no instructions designed to override the agent's core safety protocols or bypass its system prompt.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill creates an instruction file for other AI agents. While this creates a potential surface for indirect injection if a malicious user provides deceptive project details, the skill itself provides structured templates and boundary-setting guidelines which mitigate accidental obedience to embedded data.
Audit Metadata