marketing-plan
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill's workflow involves processing untrusted data from client-provided materials and external tool outputs, which presents an indirect prompt injection surface.
- Ingestion points: External data is collected from the
materials/directory (including pitch decks, transcripts, and audits) and retrieved via tool integrations with services like Ahrefs, Stripe, Shopify, and GitHub. - Boundary markers: The instructions do not specify the use of delimiters or instructions to ignore embedded commands when processing content from these external sources.
- Capability inventory: The skill can write files to the local filesystem, interact with financial and codebase APIs through various integrations, and publish content to remote GitHub repositories.
- Sanitization: There are no defined processes for sanitizing or validating external data before it is interpolated into the agent's context.
- [DATA_EXFILTRATION]: The skill fetches and processes business data and analytics from well-known services such as Stripe, Shopify, GitHub, and Google Analytics. While these integrations are required for the skill's primary purpose of financial and marketing analysis, the broad access to these platforms involves handling sensitive organizational information.
Audit Metadata