Skills
Navigate
skills/forcedotcom/sf-skills/dx-org-permission-set-assign/Gen Agent Trust Hub

dx-org-permission-set-assign

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the sf CLI via the Bash tool to perform org management tasks.
  • Evidence: The Workflow and Command Decision Table sections in SKILL.md explicitly instruct the agent to execute sf org assign permset with various flags.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it interpolates untrusted user input into shell commands.
  • Ingestion points: User-provided permission set names, org aliases, and target usernames extracted from user messages.
  • Boundary markers: No explicit delimiters or safety instructions beyond basic quoting for spaces are defined in SKILL.md.
  • Capability inventory: Full shell execution via the Bash tool as described in SKILL.md.
  • Sanitization: Limited to basic double-quoting for strings containing spaces; lacks comprehensive escaping for shell metacharacters in the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 11:34 PM
Security Audit — agent-trust-hub — dx-org-permission-set-assign