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