generators
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates within the expected scope of a code generator. It does not attempt to execute remote code, exfiltrate sensitive data, or bypass safety protocols.
- [PROMPT_INJECTION]: The skill analyzes existing project files to maintain architectural consistency. This establishes an attack surface for indirect prompt injection, as the agent may process untrusted content from the project being analyzed.
- Ingestion points: Local project files and existing code patterns described in the 'Key Principles' section of SKILL.md.
- Boundary markers: Absent; the instructions do not specify delimiters for data ingested from the project environment.
- Capability inventory: File system writes for code generation and interactive user prompts (AskUserQuestion).
- Sanitization: Not specified; the skill does not explicitly validate or sanitize content read from the project files before processing it.
Audit Metadata