experience-ui-bundle-2gp-deploy
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local project environment, which could potentially contain malicious instructions.
- Ingestion points: The skill reads and parses
sfdx-project.jsonand scans the local directory tree using thescripts/find-bundle-package-dir.shscript. - Boundary markers: No explicit delimiters or instructions are used to separate untrusted file content from the agent's internal instructions.
- Capability inventory: The skill has the ability to execute Salesforce CLI (
sf) commands, perform file system writes (metadata files), and runnpmcommands. - Sanitization: There is no evidence of validation or sanitization of inputs retrieved from the project configuration before they are used in command construction.
- [COMMAND_EXECUTION]: The skill executes
npm installandnpm run buildwithin the bundle directory. While these are standard development tasks, they involve executing third-party scripts defined in a localpackage.jsonfile. - [DYNAMIC_EXECUTION]: The skill utilizes
node -eone-liners to programmatically modifysfdx-project.json. This involves executing strings as JavaScript code to perform configuration updates.
Audit Metadata