Create Service

Warn

Audited by Gen Agent Trust Hub on Jun 1, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using user-provided input, specifically git checkout -b feat/<service-name>. Because the service name is not sanitized or escaped, an attacker can provide a name containing shell metacharacters (e.g., ;, &, |, or backticks) to execute arbitrary commands on the host system.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) by interpolating unvalidated user input directly into shell commands and file templates.
  • Ingestion points: User-controlled {name} and {service-name} variables are ingested via the skill triggers.
  • Boundary markers: There are no boundary markers or explicit instructions to ignore embedded commands within the user-provided data.
  • Capability inventory: The skill utilizes subprocess calls for git operations (git branch, git checkout).
  • Sanitization: The skill does not perform any validation, escaping, or filtering on the user-provided strings before processing them.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 1, 2026, 12:56 AM
Security Audit — agent-trust-hub — Create Service