marketing-plan
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from client-provided materials (such as decks, audits, and brand documents) stored in client-specific directories. This content is processed by the agent to synthesize various sections of the marketing plan, creating a surface for indirect prompt injection.
- Ingestion points: Untrusted content enters the agent's context through files placed in the ~/marketing-plans/{client-slug}/materials/ directory.
- Boundary markers: The skill instructions do not explicitly mandate the use of delimiters or warnings when processing untrusted client materials.
- Capability inventory: The skill can write files to the local file system and interact with numerous external services via MCPs, including GitHub, Stripe, Notion, and Customer.io.
- Sanitization: The skill proactively implements slugification and path validation for client identifiers to prevent directory traversal and unauthorized file access.
Audit Metadata