go-viral-or-die

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown-based instructions and reference materials. It does not contain any scripts, binary files, or commands that could interact with the host system or external networks.
  • [INDIRECT_PROMPT_INJECTION]: The skill collects user input about their business to provide marketing advice. 1. Ingestion points: Business details collected in Step 1 of SKILL.md. 2. Boundary markers: The instructions lack explicit delimiters for user input. 3. Capability inventory: The skill has no access to shell commands, network tools, or file system writes. 4. Sanitization: No input sanitization is performed. The lack of dangerous capabilities renders this surface benign.
  • [SAFE]: A thorough review of the skill's instructions, metadata, and reference files found no evidence of obfuscated content, hardcoded credentials, or prompt injection techniques aimed at bypassing safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 06:47 AM
Security Audit — agent-trust-hub — go-viral-or-die