d2-validate

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local bash scripts ('ensure-deps.sh', 'extract_d2.sh') and standard utilities like 'find' and 'grep' to manage environment dependencies and extract diagram code.
  • [COMMAND_EXECUTION]: Invokes the 'd2' command-line tool to validate the syntax of identified files.
  • [PROMPT_INJECTION]: The skill includes user-supplied paths from '$ARGUMENTS' directly into shell commands, creating a potential surface for indirect prompt injection or command injection if the input is malicious.
  • Ingestion points: $ARGUMENTS variable in SKILL.md
  • Boundary markers: None
  • Capability inventory: Shell execution via Bash tool (find, grep, bash, d2)
  • Sanitization: None
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 09:12 AM
Security Audit — agent-trust-hub — d2-validate