xhs-search
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external content from social media search feeds, creating an entry point for potential indirect prompt injection.
- Ingestion points: The skill accepts a 'keyword' from the user and retrieves note data through the 'search_feeds' tool (SKILL.md).
- Boundary markers: There are no instructions to the agent to treat search results as untrusted data or to ignore embedded instructions within note titles or descriptions.
- Capability inventory: Search results (including 'feed_id' and 'xsec_token') are intended to be passed to other tools such as 'xhs-explore' and 'xhs-interact', creating a potential chain of actions influenced by external data.
- Sanitization: The skill does not define any validation or sanitization protocols for the data returned by the search API before the agent processes it.
Audit Metadata