ClawHub
Back to skill

Security audit

Feedship

Security checks for vulnerabilities and agentic risk

Overview

Feedship is a disclosed RSS/feed management skill; the main caution is optional global shell mirror settings and scheduled fetching.

Install only if you trust the external feedship package and its dependencies. Prefer normal PyPI installation or a pinned release, avoid adding global mirror exports to ~/.bashrc unless you truly need restricted-network mirrors, and remember that scheduled fetching plus semantic search can store subscribed feeds and article content locally.

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 (1)

Session Persistence

Medium
Category
Rogue Agent
Content
For environments where PyPI or HuggingFace is not accessible, use mirrors:

```bash
# Add to ~/.bashrc for persistence
echo 'export HF_ENDPOINT=https://hf-mirror.com' >> ~/.bashrc
echo 'export PIP_INDEX_URL=https://mirrors.aliyun.com/pypi/simple/' >> ~/.bashrc
source ~/.bashrc
Confidence
81% confidence
Finding
The skill instructs users to append environment-variable changes to `~/.bashrc`, creating persistent session-wide configuration that affects future shell sessions. While the stated purpose is to use mirrors in restricted networks, persisting package index and model endpoints can silently redirect future installs and downloads to alternate infrastructure, increasing supply-chain and trust risks if those mirrors are compromised or inappropriate for the environment.

Static analysis

No suspicious patterns detected.