skills/jaganpro/sf-skills/sf-testing/Gen Agent Trust Hub

sf-testing

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the official Salesforce CLI (sf) to run tests and analyze coverage. This is the intended purpose of the skill and is documented in the SKILL.md and README.md files.
  • [SAFE]: The skill includes a Python hook (hooks/scripts/parse-test-results.py) to process test outputs. This script is well-structured and implements defensive practices to handle untrusted data from test results:
  • Ingestion points: CLI stdout is ingested via environment variables in the hook script.
  • Boundary markers: The script produces formatted output with clear headers like '📊 APEX TEST RESULTS' to help the agent distinguish data from instructions.
  • Capability inventory: The agent can read and write Apex class files and execute CLI test commands, which are required for the automated fix loop.
  • Sanitization: Error messages are truncated to 200 characters, significantly reducing the space available for potential prompt injection payloads.
  • [SAFE]: The provided Apex assets (e.g., assets/dml-mock.cls, assets/test-data-factory.cls) are standard industry patterns for Salesforce testing and contain no suspicious logic or external communication beyond documented Salesforce platform features.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 02:46 AM