dx-devops-test-failures-analyze

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external, untrusted data from test failure messages and Code Analyzer violations, which presents an indirect prompt injection surface.
  • Ingestion points: Test failure messages and static analysis violation payloads are processed to generate plain-language explanations (SKILL.md, Part 1 and 2).
  • Boundary markers: There are no explicit delimiters or instructions to the model to ignore potential instructions embedded within the failure data.
  • Capability inventory: The skill can execute Salesforce CLI commands to query data (sf data query) and create records (sf data create record).
  • Sanitization: No sanitization or filtering of the failure payloads is specified.
  • [COMMAND_EXECUTION]: The skill uses the Salesforce CLI (sf) to interact with the DevOps Center environment.
  • Commands: It executes sf org list, sf plugins, sf data query, and sf data create record to gather context and log remediations.
  • Context: These commands are standard for interacting with the vendor's own cloud infrastructure and are used as intended for the skill's primary purpose.
  • [EXTERNAL_DOWNLOADS]: The skill documentation instructs users to install a specific CLI plugin.
  • Package: @salesforce/plugin-agent.
  • Context: This is an official plugin from the trusted vendor (Salesforce) and is required for the environment setup.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 06:35 PM
Security Audit — agent-trust-hub — dx-devops-test-failures-analyze