Security audit
Security checks for vulnerabilities and agentic risk
The skill sends writing tasks to CellCog as advertised, with ordinary privacy and dependency-installation considerations.
Prompts and any manuscript text you include are sent to CellCog, so share confidential work only if you intend that disclosure. Review the separate CellCog dependency and use reviewed versions where possible. Check its background-notification controls for OpenClaw. This assessment covers the supplied instructions, not the external SDK or service.
The skill instructs the agent to submit the user's task prompt through CellCog's create_chat API. Although CellCog is named as the provider, the file does not explicitly warn that prompts and included unpublished writing or personal details are transmitted to a third-party service.
The setup command invokes an unpinned npm executable through npx skills, potentially downloading and running a changing package version with the agent user's privileges. A compromised upstream release could therefore execute malicious code during installation; this is a supply-chain exposure, although the static finding incorrectly describes the command as an MCP server reference.
