ClawHub
Back to skill

Security audit

jike-digest

Security checks across malware telemetry and agentic risk

Overview

This skill coherently creates a local daily digest for a Jike topic, with the main caution that reruns may clear existing digest files in the chosen output folder.

Install only if you intend to use a local `autocli` setup to fetch Jike content. Set `topic-id` and `base-dir` deliberately, preferably to a dedicated digest folder, because rerunning for the same topic and date may clear or replace existing related files there.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill performs file read/write operations and creates or clears output directories, but it does not declare permissions or otherwise communicate these capabilities to the caller. This weakens the trust boundary and can lead to unexpected filesystem modification, especially because the configured base directory points to a real user path and later steps include deletion behavior.

Missing User Warnings

High
Confidence
97% confidence
Finding
The workflow explicitly says that if the target daily directory already exists, the skill should clear files related to the current topic, but it provides no user warning, dry-run, or confirmation. Any skill that deletes existing files under a user-controlled or environment-controlled base path creates a real risk of unintended data loss, especially because the base directory is configurable.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.