experience-ui-bundle-app-coordinate

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard development tools including the Salesforce CLI (sf), npm, and npx to manage project scaffolding, dependency installation, and application building. It also utilizes a suite of local bash scripts (e.g., scripts/check-prerequisites.sh, scripts/check-sfdx-project.sh, scripts/check-phase-6-ready.sh) to perform environment validation and phase completion checks. These operations are consistent with the skill's primary purpose of application orchestration.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied natural language prompts to drive the application generation process, creating a potential surface for injection. However, it incorporates robust mitigations including a mandatory 'Requirements Analysis' step with specific logic to detect conflicting requirements (e.g., public access combined with user-specific data) and requires manual user clarification before proceeding.
  • Ingestion points: User's natural language request (processed in SKILL.md Step 1).
  • Boundary markers: Explicit conflict detection and resolution logic in STEP 1 Action #8, which requires human clarification before build plan generation.
  • Capability inventory: Execution of Salesforce CLI commands, npm/npx tools, and local bash validation scripts.
  • Sanitization: Logical validation of prompt requirements against known conflict patterns and enforcement of a strict build order with validation scripts at each phase boundary.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 01:29 AM