marketing-plan
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted sources, which could be leveraged to influence agent behavior.
- Ingestion points: The workflow involves reading files from a user-provided
materials/directory and fetching data from external services such as Ahrefs, Google Analytics, and Stripe through MCP integrations. - Boundary markers: The instructions do not explicitly mandate the use of delimiters or 'ignore' instructions when incorporating this external data into the prompt, which is a standard defense against embedded instructions.
- Capability inventory: The agent has permissions to read and write to the local filesystem (
~/marketing-plans/) and can execute network requests through authorized MCP tools. - Sanitization: There are no specified sanitization or validation steps for the content retrieved from external materials or API responses before it is processed.
Audit Metadata