viral-hooks

Pass

Audited by Gen Agent Trust Hub on Jun 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted user-provided scripts without using boundary markers or isolation instructions.
  • Ingestion points: User-provided scripts or topics enter the context via interaction with the viral-hooks skill defined in SKILL.md.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters (e.g., XML tags or backticks) to separate user data from the agent's instructions.
  • Capability inventory: Minimal risk. The skill only performs text generation based on the hooks-database.md resource and does not use any tools for network access, file system modification, or command execution.
  • Sanitization: Absent. No escaping or validation is performed on the user's input before it is interpolated into the hook formulas.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 3, 2026, 12:38 PM
Security Audit — agent-trust-hub — viral-hooks