locust
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill demonstrates installation of the 'locust' package from the Python Package Index (PyPI), which is a legitimate and well-known library for load testing.
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by generating executable scripts from user-provided service targets and behavior definitions.
- Ingestion points: User descriptions of service targets and session flows used to construct the locustfile.py (SKILL.md).
- Boundary markers: Absent; the instructions do not define clear delimiters or warnings for the agent to treat user input as untrusted data.
- Capability inventory: The generated scripts can perform network requests and are executed through system CLI commands (SKILL.md).
- Sanitization: Absent; no validation or escaping mechanisms are provided for the user-supplied data incorporated into the scripts.
Audit Metadata