marketing-plan
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple sources, including client-provided documents and external API responses, creating a surface for indirect prompt injection.\n
- Ingestion points: The skill reads files from
~/marketing-plans/{client-slug}/materials/and fetches data from external APIs like Ahrefs, GA4, and Stripe.\n - Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to ignore potentially malicious commands embedded within the ingested data.\n
- Capability inventory: The skill allows the agent to read/write local files and publish content to external GitHub repositories, which could be exploited if the agent is manipulated by injected content.\n
- Sanitization: There are no specific sanitization or validation steps outlined for processing external data before it influences the generated marketing plan.
Audit Metadata