generating-apex-test

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute standard Salesforce CLI commands (sf apex run test) to run test suites and verify code coverage as part of a developer workflow.
  • [DATA_EXPOSURE]: The workflow involves reading production and test source code to gather context for generating appropriate test classes and data factories.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes existing Apex code to generate test cases. While this is a vulnerability surface where source code comments could theoretically contain instructions to influence the agent, the skill is a standard development tool and no active injection patterns were detected.
  • Ingestion points: Target production classes and existing test files are read during the context-gathering phase (SKILL.md, Step 1).
  • Boundary markers: The instructions do not specify explicit boundary markers or delimiters for the ingested code.
  • Capability inventory: The skill has the capability to write Apex files (.cls and -meta.xml) and execute shell commands via the Salesforce CLI.
  • Sanitization: There are no explicit sanitization steps mentioned for the ingested source code content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 12:59 AM
Security Audit — agent-trust-hub — generating-apex-test