researchers-security
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): Indirect prompt injection surface detected due to the nature of the research task.
- Ingestion points: The skill utilizes
WebFetchandWebSearchtools to gather data from external sources, specifically including high-risk sources like 'Hacker community sources (forums, leaked chats)' as defined inSKILL.md. - Boundary markers: Absent. There are no instructions or delimiters provided to ensure the agent ignores malicious instructions that might be embedded in the fetched technical reports or forum posts.
- Capability inventory: The skill allows
Write,Edit,Grep, andWebFetchoperations. An attacker who successfully injects instructions into a processed security report could potentially influence these file-writing capabilities. - Sanitization: Absent. There is no logic provided to sanitize or filter the content retrieved from external URLs before the agent processes it for the research report.
Audit Metadata