skills/forcedotcom/sf-skills/education-cloud-student-recruitment-agent-configure/Gen Agent Trust Hub
education-cloud-student-recruitment-agent-configure
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an environment where an AI agent processes data from external sources, presenting a potential attack surface for indirect prompt injection.
- Ingestion points: The skill configures Knowledge article libraries and Data Cloud data streams as grounding sources for the agent (references/grounding.md).
- Boundary markers (absent): The instructions do not mandate the use of delimiters or specific prompts to differentiate system instructions from grounded data content.
- Capability inventory: The skill possesses extensive administrative capabilities, including assigning permission sets, deploying metadata, and managing Experience Cloud site configurations (references/permissions.md, references/routing.md).
- Sanitization (absent): The configuration workflow does not include explicit data sanitization or validation steps for the content ingested through the grounding mechanisms.
Audit Metadata