coding-standards
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is susceptible to indirect prompt injection via the untrusted data it is intended to process.
- Ingestion points: Processes user-provided source code during the 'writing new code' and 'code review' phases as specified in the SKILL.md trigger conditions.
- Boundary markers: Absent; the skill does not define or require the use of delimiters (e.g., XML tags or special markers) to isolate user-provided code from agent instructions.
- Capability inventory: The skill is intended for use by agents with code generation and file modification capabilities.
- Sanitization: Absent; there is no requirement or logic to sanitize instructions that might be embedded in code comments or metadata within the processed files.
- [Prompt Injection] (SAFE): No direct prompt injection patterns, bypass markers, or attempts to extract system prompts were found in the skill's instructions.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file path access, or network operations to external domains were identified.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not execute shell commands, download remote scripts, or install untrusted external packages.
Audit Metadata