paperclip-clarify
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed as a non-mutating clarification agent. It contains explicit instructions to never create or update records, goals, or projects, effectively limiting its operations to information gathering and summarization.
- [SAFE]: All external references and tools, such as the
paperclipaiCLI, the Paperclip MCP tools, and thepaperclip-wiki-fetchfunctionality, are integrated components of the vendor's ecosystem. The use of the domainpaperclip.ingis consistent with the vendor's infrastructure. - [SAFE]: The skill's ingestion of external wiki data via
paperclip-wiki-fetchis a controlled process within the agent's workflow. Because the skill lacks the capability to execute code or mutate the environment based on this input, the risk of indirect prompt injection is negligible.
Audit Metadata