sf-b2b-lwc
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather live documentation using WebSearch and WebFetch tools. This creates an ingestion point for untrusted external data that could potentially influence the agent's code generation or command execution.
- Ingestion points: Results from WebSearch queries and web content fetched from developer.salesforce.com (SKILL.md).
- Boundary markers: The skill does not provide delimiters or specific instructions for the agent to ignore or sanitize embedded prompts within the fetched documentation.
- Capability inventory: The agent has high-privilege access to tools such as Write, Edit, and Bash, which increases the impact of a successful injection attack.
- Sanitization: No validation or sanitization processes for the external documentation are defined.
- [SAFE]: The primary documentation sources listed are official Salesforce developer domains, which are recognized as well-known and trusted services.
- [SAFE]: The skill content is educational and adheres to standard Salesforce security practices, such as Lightning Web Security (LWS) restrictions on dynamic code execution.
Audit Metadata