b2c-sandbox
Warn
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (MEDIUM): The skill recommends using
npx @salesforce/b2c-clifor sandbox management. This command involves the dynamic download and execution of code from the public npm registry. As the@salesforceorganization is not included in the trusted source whitelist, this is treated as an unverifiable dependency risk. - COMMAND_EXECUTION (LOW): The skill's primary function is to execute CLI commands (
b2cornpx). This capability allows the agent to interact with the system shell, which could be exploited to run unintended flags or commands if the agent's instructions are bypassed. - PROMPT_INJECTION (LOW): The skill has a surface for indirect prompt injection. 1. Ingestion points: Untrusted data enters the context via the output of
b2c sandbox listandb2c sandbox get. 2. Boundary markers: None are present to prevent the agent from interpreting instructions embedded in sandbox metadata. 3. Capability inventory: The skill can perform destructive actions likeb2c sandbox delete. 4. Sanitization: There is no evidence of data sanitization before the agent processes command outputs.
Audit Metadata