platform-sharing-rules-generate

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the Salesforce CLI tool (sf project retrieve start, sf project deploy start) and a local bash script (scripts/count-remaining-rules.sh) to interact with Salesforce environments and analyze XML metadata files.- [EXTERNAL_DOWNLOADS]: As part of its core functionality, the skill retrieves metadata files (.sharingRules-meta.xml) from external Salesforce orgs to ensure local configurations match the live environment before performing edits or deletions.- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Salesforce orgs and user-supplied criteria strings which are interpolated into metadata.
  • Ingestion points: Phase 1 and Phase 3 read retrieved .sharingRules-meta.xml files.
  • Boundary markers: The skill follows a highly structured XML schema but does not use explicit boundary delimiters for the data content.
  • Capability inventory: Shell command execution via the sf CLI and a local bash script, plus file system write/delete operations.
  • Sanitization: The skill enforces strict Salesforce metadata schemas and platform-specific formatting rules.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 08:28 PM
Security Audit — agent-trust-hub — platform-sharing-rules-generate