cloud-architect
Fail
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: CRITICALCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous CLI commands for managing and auditing infrastructure across major cloud providers.\n
- Evidence: Includes commands for AWS EC2 peering (
aws ec2 describe-vpc-peering-connections), Azure VNet peering (az network vnet peering list), IAM role creation (aws iam create-role), and cost analysis (aws ce get-cost-and-usage,az consumption usage list).\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external requirements and discovery data to generate architecture designs, creating a surface for indirect instructions to influence agent actions.\n - Ingestion points: The 'Discovery' phase in
SKILL.mdinvolves assessing external state and requirements.\n - Boundary markers: No explicit boundary markers or warnings about untrusted requirements are present in the core instructions.\n
- Capability inventory: The skill utilizes powerful CLI tools (AWS, Azure, GCP CLI) capable of modifying cloud infrastructure and accessing financial or identity data.\n
- Sanitization: There is no evidence of sanitization or validation of user-supplied architectural constraints before they are processed by the agent.\n- [EXTERNAL_DOWNLOADS]: The skill includes a link to documentation hosted on a GitHub Pages site.\n
- File:
SKILL.md\n - Evidence:
https://jeffallan.github.io/claude-skills/skills/infrastructure/cloud-architect/is provided for further documentation.\n - Note: This URL belongs to the skill's author ('jeffallan') and is hosted on a well-known service (GitHub), though it was flagged by automated reputation scanners.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata