x-research
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from X (Twitter) via the x_search tool.
- Ingestion points: Data returned by the x_search tool (tweets, threads, profiles) is ingested into the agent context in SKILL.md.
- Boundary markers: The skill instructions do not specify the use of delimiters or clear separation between the agent's instructions and the external tweet data to prevent the agent from following instructions embedded in tweets.
- Capability inventory: The skill uses the x_search tool for data retrieval. No dangerous capabilities like file system modification or network exfiltration are present in the provided instructions.
- Sanitization: No explicit sanitization or filtering of the content retrieved from X is defined before it is processed by the agent.
Audit Metadata