rightcode-codeprobe-testing
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface
- Ingestion points: The skill uses
Read,Grep, andGlobtools to ingest untrusted source code and test files from the local project environment (e.g., scanning source directories for public methods and business logic). - Boundary markers: There are no explicit instructions for the agent to use boundary markers or to ignore instructions embedded within the processed code files during the audit process.
- Capability inventory: The skill's configuration includes
Bashtool access, providing a command execution vector if the agent is manipulated by malicious content within the audited files. - Sanitization: No sanitization, validation, or escaping of the processed file content is defined in the instructions.
Audit Metadata