permission-manager
Fail
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: HIGHCOMMAND_EXECUTIONDATA_EXFILTRATIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill enables the agent to alter its own security policy by adding or removing commands from authorized lists within the configuration.
- [DATA_EXFILTRATION]: The skill accesses and summarizes the contents of the
~/.config/opencode/opencode.jsonfile, which is a sensitive system configuration file governing the agent's runtime permissions. - [NO_CODE]: The skill contains no executable scripts or binaries, relying instead on natural language instructions to direct the agent's interaction with its own configuration files.
Recommendations
- AI detected serious security threats
Audit Metadata