build-form
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns were detected. The skill performs standard UI scaffolding tasks within a development environment. It limits shell execution to
nxandng buildcommands, which reduces the risk of arbitrary command execution. The external references are directed towards verified vendor libraries (@fundamental-ngx) and internal project paths. - [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection through the use of user-supplied arguments for code generation. This is expected functionality for a scaffolding tool and is considered low risk. 1. Ingestion points: $ARGUMENTS parameter in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Write, Edit, and restricted Bash build commands. 4. Sanitization: Not explicitly specified in instructions.
Audit Metadata