marketing-automation
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user-controlled data into instructions for an AI agent.
- Ingestion points: Untrusted data enters the context via the
marketing_briefYAML block andProduct Contextmarkdown sections. - Boundary markers: The skill relies on standard Markdown and YAML formatting to separate instructions from data, which provides weak protection against adversarial input designed to override agent behavior.
- Capability inventory: The skill is used for content generation and tracking code conceptualization; malicious input could potentially manipulate the output content or suggested tracking logic.
- Sanitization: No evidence of input validation, filtering, or sanitization of external context is present in the skill files.
Audit Metadata