browser
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
65
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./configs/microservice/bff-service/configs/agent-skills/clawhub/browser-automation/SKILL.mdSecurity
2 findings: 1 critical severity, 1 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
Two URLs are suspicious because the install process fetches and executes a remote shell script (curl | sh from astral.sh) and references a personal GitHub repo (github.com/gaxxx/bsession.git) — both are untrusted remote code sources that can distribute malware.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The prompt includes an example of passing a plaintext password as a CLI argument ("--vnc-password secret") and instructs asking the user for custom options, which would cause the agent to accept and embed secret values verbatim in commands.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow can ingest outsider-authored free text because in Fetch mode the agent opens a user-supplied URL, snapshots the rendered page content (including arbitrary attacker-controlled text/HTML), and then parses/returns that content within the agent’s LLM-visible results.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The setup/install script (scripts/install.sh) executes a remote shell script at runtime via "curl -LsSf https://astral.sh/uv/install.sh | sh", which fetches and runs remote code during skill setup.
- Repository
- UnicomAI/wanwu
- Commit
f618458
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.