architecture-designer
Fail
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes a documentation link (https://jeffallan.github.io/claude-skills/skills/api-architecture/architecture-designer/) that has been identified as malicious and blacklisted by automated URL scanners.
- [METADATA_POISONING]: The primary skill file (SKILL.md) has been flagged by reputation scanners as malicious. Furthermore, there is a discrepancy between the author identified by the platform context (nvlabs) and the author listed in the skill frontmatter (Jeffallan), which may mislead users about the skill origin.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting functional and non-functional requirements to generate architectural designs, creating a vulnerability surface for indirect prompt injection. 1. Ingestion points: User-provided system requirements and constraints. 2. Boundary markers: None present to delimit user input from instructions. 3. Capability inventory: Generates text documentation and Mermaid diagrams; no executable capabilities detected. 4. Sanitization: No sanitization or validation of input requirements is defined.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- AI detected serious security threats
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata