ab-test-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface because it is designed to ingest and process untrusted user data regarding A/B tests while having access to sensitive tools such as
Bash,Write, andEdit. The instructions do not define clear boundary markers for user-provided data nor do they specify sanitization or validation procedures for content that might be passed to code generation or shell command execution tools. This absence of defensive prompting could allow an attacker to embed malicious instructions within a data sample that the agent might then inadvertently execute or write to the filesystem.
Audit Metadata