load-testing
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various CLI tools and installation commands including brew, npm, pip, and apt-get. It includes the use of sudo for configuring system repositories and installing tool packages on Linux systems.
- [EXTERNAL_DOWNLOADS]: The skill fetches tool binaries, GPG signing keys, and JavaScript libraries from official and well-known service domains including k6.io, ubuntu.com, and public package registries.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes user-supplied parameters to generate scripts for load testing. \n
- Ingestion points: User-provided API endpoints, target URLs, and request bodies enter the agent context and are interpolated into script templates. \n
- Boundary markers: The templates provided in SKILL.md lack explicit delimiters or instructions for the agent to treat user-supplied input as untrusted data. \n
- Capability inventory: The skill enables the agent to perform network requests and execute shell commands through the generated load-testing scripts. \n
- Sanitization: No explicit sanitization or validation logic is defined to check user-provided data before it is used in executable script generation.
Audit Metadata