gsp-icons
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by reading external brand identity files (imagery-style.md) to enrich iconography specs. This is a functional requirement for the skill's primary purpose.\n
- Ingestion points: imagery-style.md (Step 1 enrichment mode)\n
- Boundary markers: Absent; the skill reads existing file content without explicit delimiters to isolate external input.\n
- Capability inventory: Write (updating imagery-style.md or iconography.md), WebSearch (for library research), AskUserQuestion (interactive feedback).\n
- Sanitization: Absent; no explicit validation or escaping of the ingested file content is performed before processing.
Audit Metadata