Security audit

Bc Calc

Security checks for vulnerabilities and agentic risk

Overview

This is a small calculator skill that transparently runs the local Unix bc tool and shows no hidden data access, persistence, or exfiltration behavior.

Install this if you are comfortable with a skill invoking your local node and bc binaries for calculator requests. Avoid feeding untrusted, huge, or intentionally non-terminating bc programs because the wrapper does not show a timeout or input validator.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger text is broad enough to match ordinary user phrasing such as general requests to 'calculate' or simple math questions, which can cause the skill to activate in many contexts without strong disambiguation. Overly broad activation increases the chance of unintended invocation, routing user input into this skill when another tool or safer handling path was intended.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The activation condition covers essentially any math-related request and does not define boundaries for mixed-intent prompts, educational questions, or requests containing incidental numbers. This ambiguity can lead to misrouting and untrusted input being processed by the skill in situations where the user did not intend raw expression evaluation, increasing the chance of unsafe or incorrect tool use.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: index.js:8