skills/kevinslin/llm/gen-notifier/Gen Agent Trust Hub

gen-notifier

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • COMMAND_EXECUTION (HIGH): The skill instructs the agent to run the terminal-notifier CLI tool by interpolating {DESCRIPTION OF JOB} and {STATUS_OF_JOB} variables directly into the shell command string. This pattern is vulnerable to shell command injection; an attacker can use backticks or $() within a task title to execute unauthorized commands.
  • PROMPT_INJECTION (HIGH): The skill is vulnerable to Indirect Prompt Injection (Category 8) because it ingests untrusted task data and uses it in a privileged command-line context.
  • Ingestion points: The {DESCRIPTION OF JOB} variable is derived from external task data, such as file names, commit messages, or PR content being processed by the agent.
  • Boundary markers: Absent. The instructions provide no delimiters or 'ignore-embedded-instructions' warnings for the job description.
  • Capability inventory: Direct shell execution via the terminal-notifier tool.
  • Sanitization: Absent. No instructions are provided to the agent to sanitize or escape shell metacharacters from the input variables.
  • EXTERNAL_DOWNLOADS (LOW): The skill requires the user to install terminal-notifier via Homebrew (brew install terminal-notifier). While Homebrew is a standard package manager, it is a third-party dependency that requires user trust.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:49 PM