platform-lsp-integrate

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to process and analyze untrusted external data, specifically Salesforce source code (Apex and SOQL) provided in the user's workspace.
  • Ingestion points: The skill ingests data from local workspace files such as .cls and .trigger files, as well as SOQL query strings extracted from code.
  • Boundary markers: The skill does not define or instruct the agent to use boundary markers (e.g., XML tags or clear delimiters) when processing the content of analyzed files to prevent the agent from obeying instructions embedded in code comments.
  • Capability inventory: The skill relies on the Bash tool to execute Salesforce CLI (sf) commands and diagnostic binaries, and the Read tool to access workspace files.
  • Sanitization: No specific sanitization or validation logic is described for handling the contents of the files before they are processed by the agent or passed to the LSP tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 07:43 AM
Security Audit — agent-trust-hub — platform-lsp-integrate