find-skills
Fail
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPERSISTENCEINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads a 'bootstrap' kit from a Tencent Cloud COS bucket (
https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/latest.tar.gz) and individual skills from the domainlightmake.site. While Tencent Cloud is a known infrastructure provider,lightmake.siteis an unverified third-party domain used for search and primary downloads. - [REMOTE_CODE_EXECUTION]: The
bootstrapcommand downloads Python scripts (skills_store_cli.py,skills_upgrade.py) and installs them directly into the user's home directory (~/.skillhub). These scripts are subsequently executed by the agent to perform management tasks, constituting a remote code execution pattern where untrusted external code is fetched and run. - [COMMAND_EXECUTION]: The script uses
subprocess.runandsubprocess.Popento interact with anopenclawbinary and to execute the newly installedskillhubCLI. It programmatically modifies configuration settings and restarts theopenclawgateway service. - [PERSISTENCE]: The installation process writes wrapper scripts (
skillhub,oc-skills) to common binary directories (~/.local/binon Linux/macOS or AppData on Windows) and applies executable permissions (chmod 0o755). This ensures that the downloaded tools remain available and executable across different user sessions. - [INDIRECT_PROMPT_INJECTION]: The
searchcommand fetches skill names and descriptions from the external API atlightmake.site. This metadata is ingested and presented to the agent, creating a surface for potential instructions embedded in external data to influence the agent's behavior during the installation workflow.
Recommendations
- AI detected serious security threats
Audit Metadata