sf-security
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill provides positive security guidance by instructing developers to store credentials in dedicated secure services like Salesforce Named Credentials or Business Manager services, explicitly advising against hardcoding them in the application source code.- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface where the agent is instructed to fetch and process external data from search results and documentation sites. While this is a standard documentation retrieval flow, it represents an ingestion point for external data into the agent's context.
- Ingestion points: External documentation and guides retrieved via WebSearch and WebFetch (SKILL.md).
- Boundary markers: The skill does not explicitly define delimiters or instructions for the agent to isolate content fetched from documentation sites.
- Capability inventory: The skill is permitted to use tools for file modification (Write, Edit) and shell execution (Bash).
- Sanitization: No specific validation or filtering instructions are provided for the content retrieved from external documentation sources.
Audit Metadata