running-load-tests
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill architecture exhibits an attack surface for indirect prompt injection.
- Ingestion points: The agent is instructed to analyze application architecture and endpoints from sources that could include untrusted project files or user descriptions.
- Boundary markers: The instructions lack explicit delimiters or guidance to ignore potential instructions embedded within analyzed data.
- Capability inventory: The skill is granted permissions to write files and execute bash commands via the Bash tool with specific prefixes (k6, jmeter, artillery, performance) as defined in the SKILL.md metadata.
- Sanitization: No mechanisms for input validation or sanitization are implemented to filter malicious content from analyzed data before it is used to generate executable load test scripts.
Audit Metadata