b2c-docs
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content fetched from external sources including Salesforce Help (help.salesforce.com) and the Salesforce Developer Center. While these are trusted sources, they represent an ingestion surface where instructions embedded in the documentation could potentially influence the agent's behavior.
- Ingestion points: Documentation content is fetched from remote URLs (e.g., sourceUrl) and presented to the agent in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the ingested documentation content.
- Capability inventory: The skill uses the b2c CLI which has capabilities for file system operations (docs download) and reads local configuration files (dw.json) for environment discovery.
- Sanitization: No explicit sanitization or filtering of the remote markdown content is described before it is processed by the agent.
Audit Metadata