skills/elvisun/newsjack/prompt-set-qa/Gen Agent Trust Hub

prompt-set-qa

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected in this skill. All instructions are focused on defining a Quality Assurance process for data validation.
  • [PROMPT_INJECTION]: The skill uses standard instructional language to define rules for the AI agent. There are no attempts to bypass safety filters, extract system prompts, or utilize known jailbreak patterns.
  • [DATA_EXFILTRATION]: The skill operates on project-specific JSON files (prompt_universe.json, prompt_architecture.json) and produces a report (prompt_qa.json). It does not reference sensitive system paths (e.g., .ssh, .env), hardcoded credentials, or network communication tools like curl or wget.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute external scripts, binary files, or packages. All logic is contained within the markdown instructions.
  • [COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or dynamic context injections (!command) present in the skill.
  • [OBFUSCATION]: The content is written in clear, human-readable Markdown. No Base64 encoding, zero-width characters, homoglyphs, or other techniques to hide content were found.
  • [EXTERNAL_DOWNLOADS]: The skill does not request any external dependencies or remote resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 02:08 PM
Security Audit — agent-trust-hub — prompt-set-qa