last30days
Fail
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: HIGHCREDENTIALS_UNSAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The script
scripts/lib/chrome_cookies.pyattempts to retrieve the Chrome Safe Storage master key from the macOS Keychain via thesecuritycommand. Additionally,scripts/lib/safari_cookies.pyandscripts/lib/cookie_extract.pyautomate the extraction of sensitive authentication cookies from local browser databases for various social media platforms. - [PROMPT_INJECTION]: The
SKILL.mdfile contains instructions (referred to as 'LAWs') that explicitly command the agent to override or supersede default tool behaviors and constraints, specifically targeting the citation requirements of the WebSearch tool. It also uses self-referential checks to force the agent to follow its internal formatting rules over global system guidelines. - [EXTERNAL_DOWNLOADS]: The
scripts/lib/setup_wizard.pyscript includes logic to automatically download and install theyt-dlputility using thebrewpackage manager at runtime if the dependency is missing. - [COMMAND_EXECUTION]: Multiple scripts execute arbitrary system commands using the
subprocessmodule, including sensitive utilities likesecurity,openssl,gh, andnode, often with user-derived inputs or to facilitate the extraction of encrypted host data.
Recommendations
- AI detected serious security threats
Audit Metadata