marketing-plan
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data (such as investor decks, transcripts, and marketing audits) from the
materials/directory to generate marketing plans. This creates a surface for indirect prompt injection where malicious instructions embedded in those documents could influence the agent's behavior. - Ingestion points: Files located within the
~/marketing-plans/{client-slug}/materials/directory (Step 1.2 inmethodology.md). - Boundary markers: The instructions lack specific delimiters or instructions to the agent to disregard potentially malicious directives within the analyzed client materials.
- Capability inventory: The skill possesses capabilities for file system writes (saving plan sections), and network operations via several MCP integrations including Stripe, Ahrefs, GA4, and GitHub.
- Sanitization: There are no documented procedures for sanitizing or filtering input data before it is processed by the LLM into the strategic plan.
Audit Metadata