sf-b2c-isml
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to use
WebSearchandWebFetchtools to retrieve live documentation and best practices from external sources before generating code. - Ingestion points: Data returned from web search results and external documentation pages enter the agent context in
SKILL.mdvia search and fetch instructions. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore potentially malicious instructions embedded within the fetched documentation content.
- Capability inventory: The skill allows access to potentially sensitive tools including
Write,Edit, andBashwhich could be manipulated if the agent follows instructions found in malicious external content. - Sanitization: No explicit sanitization, validation, or filtering mechanisms are defined for the content retrieved through network operations.
Audit Metadata