ClawHub
Back to skill

Security audit

Manage PocketSmith transactions, categories, budgets and financial data

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed PocketSmith financial API client with sensitive read access and optional writes that are disabled by default.

Install only if you trust this skill with your PocketSmith financial data. Keep POCKETSMITH_ALLOW_WRITES unset unless you are intentionally changing data, and verify transaction/category IDs before updates or deletes because those actions affect real financial records.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill explicitly requires an environment secret (`POCKETSMITH_DEVELOPER_KEY`) and performs network-backed financial API operations, but the manifest does not declare corresponding permissions. That mismatch weakens policy enforcement and review because a caller may not be clearly warned that the skill can access sensitive credentials and financial data over the network, increasing the risk of unintended data exposure or unauthorized actions if write mode is enabled.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The README states that Claude Code will 'automatically load the skill when relevant,' but it does not define meaningful scope boundaries for relevance. Because this skill can read sensitive financial data and, when an environment flag is enabled, perform write operations, ambiguous auto-activation guidance can lead to broader-than-expected invocation and unintended access or modification workflows.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The natural-language examples encourage broad, conversational triggering such as 'Show me my PocketSmith transactions' and 'Categorize transaction 123456 as Subscriptions,' which can cause an agent to invoke the skill from loosely related prompts. In a finance context, overly broad invocation increases the chance of unnecessary exposure of personal financial data or accidental state-changing actions if writes are enabled.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.