gtm-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied descriptions of their ideal customers (ICP) and pain points to generate a GTM document. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the user-provided context.
- Ingestion points: User input describing customers and pain points in
SKILL.md(Step 1), and reading.agents/product-marketing-context.md(metadata/usage instructions). - Boundary markers: None identified. The skill interpolates user input directly into the structured GTM document output.
- Capability inventory: The skill has the capability to write files to the local file system (saving to
.agents/gtm-plan.md). - Sanitization: No explicit sanitization or validation of the user-provided descriptions is performed before interpolation.
Audit Metadata