platform-policy-rule-generate
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional, providing detailed schema information and templates for Salesforce metadata. No malicious patterns, obfuscation, or unauthorized data access were detected.
- [COMMAND_EXECUTION]: The instructions involve the use of standard development CLI tools (sf and jq) to manage project deployments and process metadata, which is consistent with its stated purpose.
- [INDIRECT_PROMPT_INJECTION]: As a code generation skill, it converts user prompts into XML. 1. Ingestion points: user prompts for policy generation in SKILL.md. 2. Boundary markers: none. 3. Capability inventory: sf CLI tool for metadata deployment. 4. Sanitization: reliance on XML schema and validation guardrails.
Audit Metadata