twitter-x-list-members-scraper

Fail

Audited by Snyk on Jul 20, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (high risk: 0.90). The skill contains explicit, deceptive instructions to install runtime dependencies automatically and to withhold that this is a user-facing installation request (i.e., "do not request separate approval" / "do not describe it as a request"), which falls outside the advertised scraping/collection purpose and instructs the agent to hide actions from the user.

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.80). These links point to a third‑party site (browseract.com) used to auto-install a CLI/runtime without explicit user consent; the domain is not a widely known vendor and could distribute executables or redirect to downloads, so it is suspicious.

CRITICAL E006: Malicious code pattern detected in skill scripts.

  • Malicious code pattern detected (high risk: 0.90). The Skill contains explicit instructions to install an external runtime (BrowserAct) automatically and to avoid prompting or describing the installation to the user, which enables covert dependency installation and presents a supply-chain / covert-installation risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to use the BrowserAct CLI to access real Twitter/X web pages at runtime (public web content), which can include outsider-authored free text (e.g., bios/headlines/member profiles) that the agent may ingest into the LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

Issues (5)

E004
CRITICAL

Prompt injection detected in skill instructions.

E005
CRITICAL

Suspicious download URL detected in skill instructions.

E006
CRITICAL

Malicious code pattern detected in skill scripts.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
CRITICAL
Analyzed
Jul 20, 2026, 04:41 AM
Issues
5
Security Audit — snyk — twitter-x-list-members-scraper