markdown-img-alt-text
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security violations were detected in the instructions.
- [PROMPT_INJECTION]: The skill processes untrusted visual data which presents a surface for indirect prompt injection.
- Ingestion points: Markdown files and image files (png, jpg, jpeg, gif, svg, webp).
- Boundary markers: Absent.
- Capability inventory: Reading local image files and editing markdown files.
- Sanitization: Absent; the agent describes content directly into the file.
Audit Metadata