specialist-marketing-seo-specialist
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill interpolates untrusted user input into a sub-agent prompt without adequate security boundaries.
- Ingestion points: The variable '{the user's question}' in SKILL.md is used to capture input from the user.
- Boundary markers: The skill lacks delimiters (such as XML tags or triple quotes) or 'ignore embedded instructions' warnings that would prevent user input from overriding the sub-agent's primary instructions.
- Capability inventory: The skill utilizes the 'Agent' tool to spawn and instruct sub-agents based on the combined prompt.
- Sanitization: No validation, escaping, or filtering is applied to the content provided in the user's question.
Audit Metadata