k6-performance

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the PapaParse library from the official k6 JavaScript library repository (jslib.k6.io) to enable CSV data parsing within performance tests.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions demonstrate patterns for ingesting data from external files and network responses, creating a potential surface for instructions embedded in untrusted data to influence agent behavior.
  • Ingestion points: The scripts in SKILL.md read local CSV and JSON files using open('./data/users.csv') and open('./data/payloads.json'), and they parse remote server response bodies using JSON.parse(response.body).
  • Boundary markers: The provided templates do not include specific delimiters or instructions to ignore potential commands embedded within the ingested test data or API payloads.
  • Capability inventory: The skill facilitates the execution of performance tests via the k6 command-line tool, which performs various network operations.
  • Sanitization: There is no explicit sanitization or validation logic shown for the content retrieved from external files or network endpoints before it is processed by the script logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 02:55 PM
Security Audit — agent-trust-hub — k6-performance