e2e-testing

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The e2e_issue tool fetches content from external GitHub and GitLab issue URLs to automatically generate test cases. This creates a surface for indirect prompt injection, where malicious instructions embedded in an issue could potentially influence the agent's behavior during test generation.\n
  • Ingestion points: e2e_issue tool retrieves descriptions from external repository URLs.\n
  • Boundary markers: No explicit markers are documented for isolating the untrusted issue content.\n
  • Capability inventory: The skill can execute JavaScript via the evaluate action, write files, and perform browser-based network requests.\n
  • Sanitization: No specific sanitization process is described for the fetched issue text.\n- [COMMAND_EXECUTION]: The skill implements an evaluate action which allows arbitrary JavaScript to be executed within the browser context via Puppeteer. This is a standard but powerful testing capability.\n- [COMMAND_EXECUTION]: The skill utilizes the gh and glab CLI tools to interact with remote repositories, though it uses controlled execution to mitigate shell injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 08:25 AM
Security Audit — agent-trust-hub — e2e-testing