stitch-ui-design-spec-bootstrap
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a static design specification and template for Bootstrap-Vue. It contains no executable scripts, shell commands, or network operations. All output is limited to formatted text and JSON metadata.
- [SAFE]: All external references target legitimate and well-known Bootstrap-Vue documentation sites and official repositories. These references are documented neutrally and do not involve remote code execution or unauthorized downloads.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface as it ingests untrusted data from user requests and external documents such as PRDs (referenced in
references/official.md). The skill uses structural headers ([Context],[Layout],[Components]) as boundary markers for the assembled prompt. Analysis of all skill files confirms a complete absence of capabilities such as command execution, network operations, or file system writes. No specific sanitization logic is implemented for external content, but the lack of exploitable capabilities renders this surface safe in its current implementation.
Audit Metadata