microservices-architect
Fail
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: CRITICALINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided domain analysis and system descriptions to generate architecture strategies, creating a surface for indirect instruction injection.
- Ingestion points: The skill ingests complex architectural descriptions and monolith structures within
SKILL.mdandreferences/decomposition.mdworkflows. - Boundary markers: There are no specific delimiters or instructions for the agent to ignore potentially malicious directions embedded in the source data.
- Capability inventory: The skill provides logic for system design and provides code examples in Node.js, Python, and TypeScript; it does not have direct file-system or network tool access.
- Sanitization: No input sanitization or validation mechanisms are defined for the architectural source material.
- [EXTERNAL_DOWNLOADS]: The skill references documentation hosted on an external web domain.
- Evidence:
SKILL.mdcontains a link tohttps://jeffallan.github.io/claude-skills/skills/api-architecture/microservices-architect/for extended documentation. - Analysis: The domain is associated with the skill's author and serves as a vendor resource, though it is not included in the standard list of whitelisted services.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata