meitu-game-2d-assets

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPERSISTENCEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill requests read access to vendor-specific credential files at ~/.meitu/credentials.json for CLI authentication.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the meitu-cli package via npm to perform its primary image generation functions.
  • [PERSISTENCE]: The skill maintains project-specific state and user preferences by writing to files in the visual memory directory, including global.md, scenes/*.md, and observations.yaml.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external project files to construct prompts for image generation, creating a surface for potentially malicious instructions embedded in those files.
  • Ingestion points: The skill reads project configuration from openclaw.yaml, design guidelines from DESIGN.md, and visual memory files within ~/.openclaw/workspace/visual/.
  • Boundary markers: No explicit delimiters or isolation instructions are defined to separate ingested content from the system instructions.
  • Capability inventory: The skill has the capability to execute shell commands via the meitu CLI for generating, editing, and enhancing image assets.
  • Sanitization: There is no evidence of validation or sanitization performed on the content read from external project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 02:54 AM
Security Audit — agent-trust-hub — meitu-game-2d-assets