skills/testland/qa/checkov-policy/Gen Agent Trust Hub

checkov-policy

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the 'checkov' package from PyPI. Checkov is a widely recognized and well-known open-source utility for security linting and infrastructure auditing.
  • [COMMAND_EXECUTION]: The skill executes several command-line tools including 'pip', 'checkov', and 'terraform' to manage dependencies, execute security scans, and process infrastructure plan files.
  • [PROMPT_INJECTION]: The skill is designed to process and analyze external Infrastructure-as-Code (IaC) files, which represents a potential surface for indirect prompt injection.
  • Ingestion points: The skill reads various configuration files such as 'main.tf', 'plan.json', and entire directories containing IaC manifests.
  • Boundary markers: There are no specific delimiters or instructional constraints provided to ensure the agent ignores potential natural language instructions embedded within comments or metadata of the scanned files.
  • Capability inventory: The skill allows for package installation ('pip install') and shell command execution for scanning and infrastructure planning ('checkov', 'terraform').
  • Sanitization: The content of the files being analyzed is processed directly by the scanning tool without pre-filtering or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 10:54 AM
Security Audit — agent-trust-hub — checkov-policy