exploratory-testing

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process data from external, potentially untrusted systems during the testing process.
  • Ingestion points: Data enters the agent's context from the "system under test" (captured via browser automation, screenshots, and API responses) as well as from external charter and requirement documents.
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following malicious instructions that might be embedded within the content of the system being tested.
  • Capability inventory: The skill utilizes browser automation capabilities (navigation, API listening) and performs file write operations to the local project directory (e.g., creating markdown notes and updating the .qa/ knowledge base).
  • Sanitization: The instructions do not specify any validation, filtering, or sanitization of the data retrieved from the target system before it is recorded in testing notes or project memory.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 01:36 AM
Security Audit — agent-trust-hub — exploratory-testing