marketing-growth-hacker

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
  • Ingestion points: The skill utilizes WebFetch and WebSearch tools to retrieve content from external websites (SKILL.md).
  • Boundary markers: No delimiters or instructions are specified to separate untrusted external data from system instructions.
  • Capability inventory: The agent is granted Read, Write, and Edit permissions for local files, combined with web access tools (SKILL.md).
  • Sanitization: No mechanisms for validating or sanitizing retrieved web content are described.
  • [EXTERNAL_DOWNLOADS]: References documentation in a public repository on GitHub (msitarzewski/agency-agents).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 09:44 AM
Security Audit — agent-trust-hub — marketing-growth-hacker