browser-automation
Playwright-based browser automation patterns for autonomous web interaction
56
63%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./crates/openfang-hands/bundled/browser/SKILL.mdSecurity
1 high severity finding. You should review these findings carefully before considering using this skill.
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 skill instructs the agent to ask for user credentials and use browser_type to fill the password field, which requires the LLM to receive and emit secret values verbatim (high exfiltration risk).
Low
Low-risk findings.
1 low severity finding. 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
This workflow is a general web browser that will use `browser_read_page` (and likely `web_fetch`) to ingest the contents of pages it navigates to at runtime, and those pages are outsider-authored free text (public web content) that can include prompt-injection payloads.
- Repository
- RightNow-AI/openfang
- Commit
acf2587
- 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.