Security audit
Security checks for vulnerabilities and agentic risk
The skill is not overtly malicious, but its Excel branding does not match its broad command-capable automation instructions, so it should be reviewed before installation.
Review this skill carefully before installing. Only use it in a sandboxed workspace where command execution and file writes are acceptable, avoid sensitive spreadsheet data until the external API/data-flow story is clarified, and require explicit approval for any shell command or filesystem mutation.
The skill is marketed as an Excel spreadsheet generator, but the documented behavior is a generic LLM content processor. This mismatch can cause users or calling agents to grant file-write and command-execution privileges under false assumptions, increasing the risk of misuse, unexpected data handling, or unsafe execution in contexts that expected a narrow spreadsheet-only capability.
The feature table advertises Excel-specific professional generation, while the rest of the document describes broad content generation and generic automation behavior. This inconsistent scope is dangerous because it disguises the effective capability of a skill that also has exec/write tools, making risk assessment and safe delegation much harder for users and agents.
The invocation guidance is broad and ambiguous, covering data analysis, reporting, visualization, automation, and general integration scenarios without clear boundaries. In the context of a skill with read/exec/write capabilities, vague triggering criteria increase the chance that an agent will invoke it in inappropriate or overly privileged situations.
The skill declares read, exec, and write tools but does not prominently warn users that it may execute commands or modify files. Hidden or underemphasized privileged behavior creates a safety issue because users may assume a harmless document generator while actually authorizing filesystem changes and shell execution.
The output contract describes JSON/text/markdown responses rather than spreadsheet artifacts, contradicting the Excel-focused branding. This can mislead orchestrators and users about what files will be produced and what downstream processing is safe, enabling accidental exposure of data to an LLM workflow instead of a local document-generation path.
Requiring an external API key and LLM dependency for a purported Excel-generation skill introduces unnecessary external data flow and secret handling that are not justified by the stated local spreadsheet purpose. Users may send sensitive spreadsheet content to third-party services without realizing it, creating confidentiality and compliance risks.
No suspicious patterns detected.
