national-expungement-expert
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it ingests external content to fulfill its purpose. Ingestion points: Data enters the agent via the
WebSearchandReadtools. Boundary markers: Absent; there are no instructions provided to the agent to distinguish between internal instructions and potentially malicious data embedded in web search results. Capability inventory: The toolset is limited to information gathering (Read,Glob,Grep,WebSearch) and internal task management (Task); no tools for arbitrary shell execution, persistent file writing, or network exfiltration are present. Sanitization: No sanitization or filtering of external content is specified. - [Data Exposure] (SAFE): No hardcoded credentials or sensitive file paths were detected in the skill configuration.
- [Remote Code Execution] (SAFE): No patterns for remote code downloads or execution were found.
Audit Metadata