marketing-plan
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data provided by users in the materials directory to generate marketing plans. \n
- Ingestion points: Files located in the ~/marketing-plans/{client-slug}/materials/ directory are read during the INIT phase to gather context for the marketing plan.\n
- Boundary markers: The instructions do not currently prescribe the use of specific delimiters or 'ignore' markers to encapsulate user-provided materials during processing.\n
- Capability inventory: The skill has the capability to write local files, perform Git operations (clone, commit, push), and invoke numerous external APIs and MCPs (such as Stripe, Ahrefs, and Shopify).\n
- Sanitization: While robust path safety and directory scoping are implemented to prevent traversal attacks, there is no explicit sanitization or filtering of the content ingested from external documents to prevent the execution of embedded instructions.\n- [EXTERNAL_DOWNLOADS]: The skill documentation describes a marketing operations stack that includes integrations with well-known professional services (Stripe, Ahrefs, Shopify, Notion) and common browser automation tools. These references are instructional and describe legitimate tooling integrations for fractional CMO workflows.
Audit Metadata