oma-debug
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for software maintenance and actively promotes security best practices through its internal documentation and examples.
- [PROMPT_INJECTION]: The skill presents an inherent surface for indirect prompt injection due to its core function of processing untrusted bug reports and external codebase files. * Ingestion points: User-provided bug reports and source code files accessed via search tools in resources/execution-protocol.md. * Boundary markers: No explicit delimiters or 'ignore' instructions are used to wrap processed content. * Capability inventory: Employs Serena MCP for code navigation and possesses the capability to modify source files to apply fixes. * Sanitization: The skill does not explicitly describe input sanitization for the reports it processes.
- [EXTERNAL_DOWNLOADS]: The resource files (resources/common-patterns.md) suggest the installation of standard security auditing tools such as bandit and safety via official package managers.
- [COMMAND_EXECUTION]: Recommends the execution of reputable security and testing CLI tools (e.g., bandit, safety, pytest) to verify code integrity and security.
Audit Metadata