skills/dwsy/agent/svg-logo-generator/Gen Agent Trust Hub

svg-logo-generator

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The Python scripts (logo_generator.py, logo_tech.py, logo_v2.py) execute file system write operations to save generated SVG content. All scripts use a hardcoded absolute path (/Users/dengwenyu/Dev/AI/folder-site/public/logo.svg) which may cause errors or unintended file overwrites if the environment differs.
  • [DATA_EXFILTRATION]: The source code reveals sensitive environment metadata, specifically the local system username ('dengwenyu') and the author's internal directory structure, through the hardcoded absolute paths.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted user input (design metaphors, colors, and text) and interpolates it directly into SVG templates via f-strings. This content is then written to the local disk without sanitization, allowing for potential SVG injection or malicious file content generation.
  • Ingestion points: User requests for design metaphors and visual identity planned in the 'Design Analysis' section of SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: File-write operations (open().write()) present in all Python script files.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 06:09 AM