dx-devops-promote
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a legitimate DevOps workflow using official Salesforce developer tools (sf CLI). It follows best practices for headless CLI interaction, such as using JSON output and record IDs.
- [COMMAND_EXECUTION]: The skill generates shell commands for the sf CLI to perform promotion tasks. These operations are scoped to the intended purpose of the skill and do not involve arbitrary code execution or privilege escalation.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from CLI outputs (e.g., VALIDATE_JSON). It employs robust boundary markers by requiring the use of jq for parsing and record IDs for command flags, minimizing the risk of the agent being misled by unexpected data content. Evidence chain: 1. Ingestion points: VALIDATE_JSON in SKILL.md; 2. Boundary markers: JSON structure and jq extraction; 3. Capability inventory: sf devops CLI operations; 4. Sanitization: Instruction to avoid shell interpolation of user-supplied IDs.
Audit Metadata