forge-spacing-fix
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and does not distribute any executable code, scripts, or binary files.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external audit data, which creates a potential surface for indirect prompt injection. 1. Ingestion points: Data input from '/forge-spacing-audit' mentioned in SKILL.md. 2. Boundary markers: The instructions do not define explicit delimiters for separating audit data from instructions. 3. Capability inventory: The agent is instructed to modify text (design tokens) within project files. 4. Sanitization: No automated sanitization is described, but the skill includes a safety constraint requiring human confirmation for value adjustments greater than 4px.
Audit Metadata