sp-define-product
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from a user-editable file, which serves as a potential vector for indirect prompt injection.
- Ingestion points: The agent is instructed to read
PRD.mdfrom the project root before updating it or using its content to generate UI mocks. - Boundary markers: There are no instructions to use delimiters or ignore potential commands embedded within the
PRD.mdcontent. - Capability inventory: The skill has the capability to read/write files and trigger other tools such as
sp-new-ui-mockandsp-clone-prototypebased on the content of the processed file. - Sanitization: The skill lacks explicit sanitization or validation logic to filter out instructional content from the data read from
PRD.mdbefore it is interpolated into the agent's context.
Audit Metadata