gtm-sprint
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates untrusted user input into a complex automated workflow.
- Ingestion points: The skill ingests untrusted data through the
[product]argument provided by the user when executing the/gtm-sprintcommand inSKILL.md. - Boundary markers: No explicit delimiters, such as XML tags, triple-backticks, or instructions to ignore embedded commands, are present to isolate the user-provided product description from the agent's core instructions.
- Capability inventory: The skill utilizes tool chaining (calling other internal skills like
/icp-modeller,/seo-audit, etc.) and interacts with the Keywords Everywhere API (using a key referenced intopics/api-keys.md) to perform market research and content generation. - Sanitization: There is no evidence of sanitization, filtering, or validation of the product input before it is used to influence the agent's behavior and output generation.
Audit Metadata