design-sprint
Warn
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: MEDIUMMETADATA_POISONINGINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [METADATA_POISONING]: The skill contains inconsistent instructions that do not align with its primary purpose. While the skill is titled 'Design Sprint', sections such as 'What Claude Does vs What You Decide' and 'Skill Boundaries' describe video production tasks including shot composition and videography.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-defined sprint challenges and participant information which are used to generate the sprint activities. 1. Ingestion points: User input variables [challenge] and [who's involved] are requested in the 'How to Use' section. 2. Boundary markers: No delimiters are used to wrap user input. 3. Capability inventory: The skill is instruction-based and does not contain scripts or network tools. 4. Sanitization: Absent.
- [EXTERNAL_DOWNLOADS]: The skill references an external Model Context Protocol (MCP) server package '@clawfu/mcp-skills' in the frontmatter.
Audit Metadata