design-sprint
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a mode to update existing files, which creates an attack surface for indirect prompt injection.
- Ingestion points: The skill searches for and reads sprint plan documents from directories including product/, design/, sprints/, and planning/, or from paths provided via user input.
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat loaded file content as untrusted or to ignore embedded instructions.
- Capability inventory: Functionality is limited to reading local files and writing markdown documentation; there are no network operations, subprocess executions, or dynamic code evaluation tools defined.
- Sanitization: The skill does not provide methods for sanitizing, validating, or filtering content retrieved from ingested files before the agent processes it.
Audit Metadata