forge-grid
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to scan and modify external codebase files, which constitutes a vulnerability surface for indirect prompt injection if those files contain adversarial content.
- Ingestion points: Reads padding, margin, and gap declarations from codebase files (SKILL.md).
- Boundary markers: None defined to isolate the codebase content from the agent's instructions.
- Capability inventory: The skill performs codebase-wide scanning (read) and variable replacement (write/edit).
- Sanitization: No validation or sanitization of the ingested CSS/spacing values is specified.
Audit Metadata