dx-org-permission-set-assign

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or supporting files. The skill correctly implements the Salesforce CLI 'sf' for org management tasks.
  • [PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection (Category 8) as it processes user-provided inputs like permission set names and usernames for interpolation into shell commands. This is standard functionality for a CLI-wrapping skill. Given the official vendor context (forcedotcom) and the inclusion of basic input guidance, this is documented as a functional surface rather than a malicious finding.
  • Ingestion points: User-provided permission set names, org aliases, and target usernames extracted from the request as described in SKILL.md.
  • Boundary markers: The instructions do not define strict shell delimiters but do instruct the agent to use specific command flags.
  • Capability inventory: The skill uses the Bash tool to execute sf org assign permset commands.
  • Sanitization: The skill provides guidance in the 'Gotchas' section to wrap names containing spaces in double quotes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 11:19 AM
Security Audit — agent-trust-hub — dx-org-permission-set-assign