ClawHub
Back to skill

Security audit

Digest Builder

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a legitimate FreshRSS digest builder that uses an API password and saves feed content locally as part of its stated purpose.

Install only if you are comfortable giving the skill access to your FreshRSS API password and saving unread feed titles, links, excerpts, summaries, and reading-history-derived files under the digest output paths. Use a FreshRSS API password rather than your web login password, review generated files before sharing them, and run the mark-as-read helper only deliberately, preferably with dry-run and date filtering first.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly instructs the agent to read FreshRSS credentials (`api_password`) and write multiple output files, but it does not require user confirmation, disclose the sensitivity of the secret, or constrain where data is stored. In an agent setting, this can lead to unintended secret access and filesystem modification beyond what the user realizes they are authorizing.

Static analysis

No suspicious patterns detected.