zread-expert
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill demonstrates a clear and legitimate purpose for codebase auditing and architectural analysis. No patterns associated with data exfiltration, command injection, or privilege escalation were detected. The usage of the
zreadtoolset is consistent with the skill's description and metadata.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (GitHub repositories), which serves as an ingestion point for potentially untrusted content that could contain embedded instructions.\n - Ingestion points: Data is fetched through
zread.read,zread.search, andzread.structureas described inSKILL.md.\n - Boundary markers: None. There are no specific instructions for the agent to treat repository content as untrusted or to ignore embedded instructions within code comments or documentation.\n
- Capability inventory: The skill's capabilities are limited to the
zreadtoolset. It does not have access to general shell execution, file system writing, or arbitrary network requests beyond the tool's intended scope.\n - Sanitization: The skill relies on the underlying agent's standard safety protocols and does not provide custom sanitization for repository data.
Audit Metadata