ab-test-setup
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown-based instructions, best practices, and templates for experimentation design. There are no executable scripts, system commands, or attempts at obfuscation.
- [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection by instructing the agent to ingest external local context.
- Ingestion points:
.agents/product-marketing-context.md(referenced in SKILL.md). - Boundary markers: Absent.
- Capability inventory: The skill does not possess any dangerous capabilities such as file system writing, network exfiltration, or subprocess execution.
- Sanitization: Absent.
- Context: The ingestion of the product marketing context file is a standard practice for this agent to gain necessary domain knowledge and does not pose a risk given the lack of exploitable actions available to the skill.
Audit Metadata