The Agent Skills Directory

Unverifiable Dependencies (LOW): The skill relies on the @salesforce/b2c-cli package via npx. Since @salesforce is not on the predefined list of trusted organizations, this is classified as an external dependency. The severity is downgraded from MEDIUM to LOW because it is essential to the skill's primary purpose.
Data Exposure & Exfiltration (LOW): The b2c docs download command communicates with external Salesforce domains (e.g., *.demandware.net). These domains are not in the approved whitelist. Severity is LOW as these connections are required to fetch documentation.
Indirect Prompt Injection (LOW): The skill reads and processes external data (API docs and XSD schemas) which could theoretically contain malicious instructions.
Ingestion points: Terminal output from b2c docs read and b2c docs schema commands.
Boundary markers: Absent; the skill does not wrap tool outputs in specific delimiters or safety warnings.
Capability inventory: The skill has the ability to execute shell commands and write files to the local system via the b2c CLI.
Sanitization: No evidence of sanitization or content validation is present for the fetched documentation.

b2c-docs