marketing-plan
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted client materials to generate marketing strategies, which is a standard functional surface for this type of agent.
- Ingestion points: The skill reads all available materials provided by the user in the '~/marketing-plans/{client-slug}/materials/' directory during the INIT phase, as described in Step 1.2 of references/methodology.md.
- Boundary markers: There are no explicit instructions to use delimiters or 'ignore' warnings for the embedded content within these external files.
- Capability inventory: The skill has the capability to read and write files within the user's marketing-plans directory and can invoke external MCP tools such as Ahrefs, Stripe, and GA4.
- Sanitization: No specific sanitization or filtering mechanisms for the ingested client data were identified in the methodology instructions.
Audit Metadata