lightning-architecture-review
Fail
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references several external URLs for documentation and research purposes. Specifically, it points to a GitHub repository (github.com/8144225309/SuperScalar) and a project website (SuperScalar.win). Additionally, it references a discussion on delvingbitcoin.org, which was flagged by automated security scanners as a malicious URL. Notably, the skill's instructions explicitly warn the agent that the community implementation at 8144225309/SuperScalar returned an HTTP 404 and should not be treated as a verified or audited source.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze complex protocol designs provided by users, which creates a potential surface for indirect prompt injection. Ingestion points: User-provided protocol architecture and design descriptions (SKILL.md). Boundary markers: None identified. Capability inventory: The skill does not define access to file-writing, network execution, or shell command tools. Sanitization: No sanitization or validation of the input content is specified before the analysis process.
Recommendations
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata