agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Security
3 findings — 1 critical severity, 1 high severity, 1 medium 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
Suspicious download URL detected (high risk: 0.75). The list mixes legitimate/documentation pages (github.com login, lightpanda.io docs, example.com) with explicit malicious domain(s) and several ambiguous/untrusted hosts (site-a.com, site-b.com, app.example.com variants, localhost/staging/prod endpoints) — because the skill asks to download/execute from these URLs, the presence of an explicit malicious domain and multiple unknown third‑party hosts makes this a moderately high risk for malware distribution.
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
Insecure credential handling detected (high risk: 0.90). The prompt includes examples and workflows that embed plaintext secrets and tokens into commands and saved state (e.g., fill "password123", echo "pass" | agent-browser auth save", state files containing session tokens), so an LLM using this skill may be required to output secret values verbatim.
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
Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly lets the agent "open <url>", snapshot/get text from pages, and interact with arbitrary websites (e.g., "agent-browser open https://example.com", "agent-browser snapshot -i", "agent-browser get text body > page.txt") and also states "By default, agent-browser imposes no restrictions on navigation, actions, or output," so the agent will ingest untrusted third‑party web content that can influence subsequent actions.
- Repository
- brianlovin/claude-config
- Commit
1a9819e
- 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.