shared-core
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a configuration template for agent coordination and does not contain any malicious instructions or patterns.
- [COMMAND_EXECUTION]: The instructions explicitly limit the use of the bash tool to legitimate development activities such as git operations, running tests, and building software, which reduces the attack surface for arbitrary command execution.
- [DATA_EXFILTRATION]: Network capabilities via the fetch tool are described within the context of a message-passing architecture. No patterns for harvesting credentials or accessing sensitive system files (e.g., .ssh, .aws) were identified.
- [SAFE]: File system interactions are restricted to a localized session directory (./.claude/session/) for managing agent state and communication logs, preventing unauthorized access to the broader file system.
Audit Metadata