web-asset-generator

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (scripts/generate_favicons.py and scripts/generate_og_images.py) and standard shell utilities (cp, find, grep) to manage files and detect project frameworks.\n- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of standard Python packages (Pillow, pilmoji, emoji) from the official PyPI registry to support image processing and emoji functionality.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted user-supplied slogans and reads project files (e.g., package.json, layout.tsx) to generate content and suggest code changes.\n
  • Ingestion points: User-provided slogans via command-line arguments and project configuration files.\n
  • Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the guidelines.\n
  • Capability inventory: The skill can execute Python scripts, run shell commands, and modify project files using the Edit tool.\n
  • Sanitization: No specific sanitization or validation logic is described for the input slogans or file contents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 01:28 PM
Security Audit — agent-trust-hub — web-asset-generator