SkillTotal

Is @promptbook/remote-client safe?

No malicious indicators - review capabilities before installing
Notable — review in context (capabilities are not malware):
  • Node.js shell/command execution
  • Node.js dynamic code execution

@promptbook/remote-client is an AI npm_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 2 risky constructs are reported for review. It can: dynamic code execution and shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

@promptbook/remote-client 0.114.0-41

npm_package · npm:@promptbook/remote-client
LOW
0
/ 100 risk score
Snapshot · scanned Sep 27, 2026 · @promptbook/remote-client@0.114.0-41 · engine 0.53.0 / ruleset 60

Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of @promptbook/remote-client's authors. Report a false positive.

Capabilities — what this component can do (not a risk score):
dynamic code executionshell execution

Behavioral traits

How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.

Execution authority
Tool Access Control / Direct Tool Access

Findings (2)

HIGHNode.js dynamic code executionST-DYN-NODE

The code turns strings into live code at runtime (eval / new Function / exec).

eval(script); // <- TODO: Use `JavascriptExecutionTools.execute` here
eval(script); // <- TODO: Use `JavascriptExecutionTools.execute` here

Why it matters: If those strings aren't fixed and trusted, they become a way to run arbitrary code.

Fix: Avoid evaluating dynamically constructed code; if unavoidable, ensure the input is a trusted constant and never derived from external data.

HIGHNode.js shell/command executionST-SHELL-NODE

The component can run operating-system commands or spawn processes.

Why it matters: Powerful and often legitimate — confirm the commands aren't built from untrusted input.

Fix: Confirm the command and its arguments are fully controlled and not derived from untrusted input; prefer execFile with an argument array.

Check your own component

Run the same evidence-backed scan on any MCP server, agent skill, or package.

Scan your own component

How we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →