company-creator
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted third-party git repositories. This provides a surface for indirect prompt injection where malicious instructions embedded in a repository's README or code could attempt to manipulate the agent during the company generation process.
- [EXTERNAL_DOWNLOADS]: Fetches normative specifications from
agentcompanies.ioand references code/skills from thepaperclipaiGitHub organization. These are recognized as trusted vendor and protocol resources and do not contribute to a higher severity verdict. - [COMMAND_EXECUTION]: Uses
git clone,git ls-remote,curl, andwgetto interact with external repositories and download documentation. These commands are necessary for the skill's primary purpose of repo analysis and package generation.
Audit Metadata