search
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from a Notion workspace, which could contain malicious instructions designed to influence the agent.
- Ingestion points: Search results and database query outputs retrieved from the Notion workspace (SKILL.md).
- Boundary markers: The skill does not provide specific instructions to the agent on how to delimit or isolate external data from its own instructions.
- Capability inventory: The skill includes summarization and search capabilities; there are no dangerous capabilities such as file system writing, command execution, or network exfiltration in the provided instructions.
- Sanitization: No logic is defined to sanitize, escape, or validate the content retrieved from the workspace before it is processed.
- [NO_CODE]: The skill is composed entirely of markdown instructions and metadata, without any scripts, binaries, or executable files.
Audit Metadata