sf-catalog
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to ingest untrusted data from external web sources, creating a surface for indirect prompt injection.
- Ingestion points: Usage of
WebSearchandWebFetchtools to retrieve "live docs" as specified inSKILL.md. - Boundary markers: Absent. The instructions do not provide delimiters or clear guidance to the agent to ignore potential instructions embedded in the external documentation.
- Capability inventory: The skill has access to powerful tools including
Bash,Write, andEdit, which could be abused if the agent obeys instructions hidden in fetched content. - Sanitization: Absent. There is no mention of validating or filtering the content retrieved from external URLs before processing it.
Audit Metadata