backend-expert
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The metadata includes an installation command that fetches the skill's markdown file from a public GitHub repository. This is a standard deployment mechanism and does not involve executing remote code or scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided technical requirements to generate advice and code, creating a surface for external data ingestion. However, the skill lacks access to tools or execution environments that would permit exploitation.
- Ingestion points: The skill analyzes user-provided technology stacks and requirements in
SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are provided.
- Capability inventory: The skill is restricted to textual and code generation and does not utilize shell tools, file-writing scripts, or network utilities.
- Sanitization: No input validation or sanitization logic is defined for the requirements analysis.
Audit Metadata