workflow-preflight

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to discover and execute shell commands from the codebase, such as scripts in package.json, Makefile targets, or language-specific test runners.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by extracting and executing commands found in untrusted project documentation and configuration files.
  • Ingestion points: The skill reads commands from README.md, package.json scripts, and .github/workflows/*.yml.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are used when interpolating these commands into the shell.
  • Capability inventory: The skill uses the Bash tool, allowing for arbitrary command execution on the host.
  • Sanitization: There is no evidence of validation or sanitization for the commands extracted from external files.
  • [EXTERNAL_DOWNLOADS]: The skill pulls the official semgrep/semgrep image from Docker Hub and utilizes package managers to run remote tools. These operations target well-known and trusted technology services.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 12:48 PM