ab-testing

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external context files to tailor its experimentation advice.
  • Ingestion points: SKILL.md instructs the agent to read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md to establish product context.
  • Boundary markers: The skill does not employ boundary markers or specific instructions to disregard potentially malicious commands within the ingested files.
  • Capability inventory: The skill is restricted to generating text-based advice and documentation (e.g., test plans, analysis summaries). It does not have access to tools for command execution, network exfiltration, or unauthorized file system access.
  • Sanitization: No sanitization or validation is applied to the content read from these external files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:14 AM
Security Audit — agent-trust-hub — ab-testing