ssl-cert-check

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The workflow relies on executing bash commands via openssl to inspect remote endpoints. These commands are executed in a shell environment, which is a powerful capability.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (specifically command injection) by interpolating the user-provided $HOST variable directly into shell commands without sanitization.
  • Ingestion points: The hostname input provided by the user in response to triggers like "Check the SSL cert on example.com".
  • Boundary markers: No delimiters or safety instructions (e.g., "ignore embedded characters") are used when the variable is placed into the shell script blocks.
  • Capability inventory: The skill uses shell execution for openssl, grep, and echo operations across multiple steps in SKILL.md.
  • Sanitization: The instructions do not include logic to validate the hostname or escape shell metacharacters (e.g., ;, &, |) before the agent executes the commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 09:54 AM
Security Audit — agent-trust-hub — ssl-cert-check