Skills
skills/shipshitdev/skills/micro-landing-builder/Gen Agent Trust Hub

micro-landing-builder

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts scripts/batch_create.py and scripts/deploy_vercel.py utilize subprocess.run to execute local shell commands. These commands are used for project scaffolding (python3 scaffold.py) and deployment operations using the vercel CLI tool.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface in its batch creation logic.
  • Ingestion points: scripts/batch_create.py reads external data from CSV and JSON files to define project parameters.
  • Boundary markers: None; external input is parsed and directly interpolated into configuration files and command-line arguments.
  • Capability inventory: The skill can perform file system writes and execute subprocesses based on the processed data.
  • Sanitization: The script uses standard csv and json library parsers and performs basic string stripping, but lacks rigorous validation for field content which is eventually used in code generation templates in scripts/scaffold.py.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 09:45 AM