ab-test-store-listing

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides strategic advice and templates for designing A/B tests. No malicious instructions, obfuscation, or dangerous system commands were found.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read a local file (app-marketing-context.md) which presents a surface for indirect prompt injection. However, because the skill defines no executable capabilities (such as network access, subprocess execution, or file modification), this risk is not exploitable in this context.
  • Ingestion points: SKILL.md (reads app-marketing-context.md);
  • Boundary markers: Absent;
  • Capability inventory: No scripts or tools with executable capabilities are defined in this skill;
  • Sanitization: Absent
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 06:42 PM
Security Audit — agent-trust-hub — ab-test-store-listing