rightcode-codeprobe-architecture
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
- Ingestion points: Untrusted data enters the agent context via the reading of project source files using
Read,Grep, andGlobtools (SKILL.md). - Boundary markers: While markers are used for pre-computed dependency JSON, they are absent for raw source code content processed during analysis.
- Capability inventory: The skill can execute shell commands via
Bashand perform extensive file system operations (SKILL.md). - Sanitization: There is no evidence of sanitization or explicit instructions for the agent to ignore directives embedded within the scanned code files.
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to execute local Python scripts (dependency_mapper.pyandfile_stats.py). These scripts facilitate automated dependency mapping and codebase metric collection essential for the architectural review process.
Audit Metadata