Versioned security assessment

Report ID: SA-386280A6

2/15/2026, 8:42:02 AM

agent-browser security assessment v1

Skill Security Certification Report

Audit History
Audit model: claude Historical report
Skill name
agent-browser
Version
v1
Maintainer
inference-sh-0
Source
github.com/inference-sh-0/skills/tree/main/skills/agentic-browser/
Coverage
10 Files scanned · 2,310 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Low

1 confirmed security finding requires attention.

Installation context

Historical evidence

This report may not describe the currently installable artifact. Open the current Skill page for install guidance.

Open current Skill page

This report does not block or authorize the manifest or ZIP.

This is a legitimate browser automation skill using Playwright via inference.sh CLI. The static scanner flagged 606 potential issues, but upon evaluation, all findings are false positives: external_commands detections are bash command examples in documentation, network detections are legitimate test URLs, and the heuristic 'dangerous combination' flag describes expected browser automation behavior (network access + code execution + session management). This skill provides standard web automation functionality for AI agents.

Report position

Historical report

Open audit history before using this report to install.

Audit attestation

Not attestable

The required immutable binding is incomplete.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

10 Files scanned · 2,310 Lines analyzed

3 items shown for review

Limitations

This report does not claim runtime or sandbox execution and does not prove the absence of side effects.

Evidence chain

Follow the evidence from source binding to the install contract. Available evidence supports verification; it is not a safety guarantee.

  1. Source

    Binding unavailable

  2. Artifact

    Identity incomplete

  3. Audit

    Complete

  4. Install contract

    Open manifest to verify

    Open manifest

Capabilities observed

Observed means this report recorded supporting evidence. Not recorded does not prove that a capability is absent.

Contains scripts

May execute code included with the Skill.

Not recorded by this audit

Network access

May connect to external services.

Observed in 2 evidence locations

Filesystem access

May read or write local files.

Observed in 1 evidence location

Env variables

May read values from the process environment.

Not recorded by this audit

External commands

May invoke commands or programs outside the Skill.

Observed in 5 evidence locations

Capability review items (2)
Low
SKILL.md:34-37SKILL.md:114-118SKILL.md:213-215
Documentation Contains Shell Command Examples
The skill documentation includes bash scripts showing CLI usage. Command substitution syntax is for examples, not actual execution.
Low
SKILL.md:9-11SKILL.md:20
Example URLs in Documentation
Documentation contains test URLs like example.com and google.com - standard practice for technical documentation.

Risk findings

Confirmed security concerns are separated from items that still need review.

Confirmed security concerns (1)

RISK-001 Low
references/session-management.md:20-21references/session-management.md:67-69
Browser Session Management
Skill manages browser sessions including cookies and authentication state. This is core browser automation functionality, not credential access vulnerability.

Expert evidence

Immutable subject identity, scanner metadata, dismissed matches, and source-level evidence.

Artifact subject

Marketplace commit
Unavailable
Content hash
Unavailable
Tree hash
Unavailable
Skill path
Unavailable
Audit payload hash
Unavailable

Analysis metadata

Audit model: claude

Analysis state: Complete

Scope is limited to the recorded files, lines, methods, and evidence. No runtime or sandbox execution is claimed.

Verify and export

JSON report CITATION.cff SARIF 2.1.0 Signed installation manifest

The manifest and lockfile bind install artifacts to cryptographic hashes. This integrity claim is separate from the security assessment.

Audit attestation: not_attestable