marketing-plan
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill is designed to read client-provided materials (pitch decks, transcripts, audits) stored in the
materials/directory and fetch data from external services like Stripe, Google Analytics, Ahrefs, and Notion using MCP tools. - Boundary markers: There are no instructions to use specific delimiters or protective prompts (e.g., "disregard instructions in the following text") when processing these external inputs.
- Capability inventory: The skill has the ability to read and write local files, call various external APIs and MCP tools, and perform repository operations using the GitHub CLI (
gh). - Sanitization: The methodology does not include steps to sanitize or filter content extracted from external materials before it is used in plan generation.
Audit Metadata