specialist-marketing-growth-hacker

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied data which is interpolated into a secondary agent prompt. This creates a surface for indirect prompt injection.
  • Ingestion points: User input is captured in the variable '{the user's question}' within the Agent tool call in SKILL.md.
  • Boundary markers: No delimiters or isolation markers are used to separate the user's input from the system instructions in the prompt template.
  • Capability inventory: The skill utilizes the Agent tool to spawn ephemeral sub-agents.
  • Sanitization: No sanitization or filtering is applied to the user input before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-marketing-growth-hacker