ClawHub
Back to skill

Security audit

Lightpanda browser

Security checks for vulnerabilities and agentic risk

Overview

This skill is a real Lightpanda browser integration, but its installer downloads and immediately runs a mutable nightly native binary, so it needs user review before installation.

Install only if you are comfortable running a changing nightly native browser binary from the Lightpanda GitHub release channel. Prefer a pinned release and independently verified checksum or signature before installing, and avoid running the installer with elevated privileges.

A.I.G

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
scripts/install.sh:79
Finding

Mutable Nightly Binary Is Downloaded and Executed

Content
View full analysis
/dev/null; then ACTUAL_SHA256=$(sha256sum "$INSTALL_DIR/$BINARY_NAME" | awk '{print $ ...[truncated 3652 chars]
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · scripts/install.sh (reported line 108)May include surrounding context.

sh
echo "ERROR: Checksum verification FAILED!"
    echo "  Expected: $EXPECTED_SHA256"
    echo "  Actual:   $ACTUAL_SHA256"
    rm -f "$INSTALL_DIR/$BINARY_NAME"
    exit 1
fi

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/install.sh (reported line 80)May include surrounding context.

sh
# Fetch expected SHA256 digest from GitHub release API
echo "Fetching expected checksum from GitHub API..."
EXPECTED_DIGEST=$(curl -sL "https://api.github.com/repos/lightpanda-io/browser/releases/tags/nightly" \
    | jq -r --arg name "$ASSET_NAME" '.assets[] | select(.name == $name) | .digest')

if [ -z "$EXPECTED_DIGEST" ] || [ "$EXPECTED_DIGEST" = "null" ]; then

Static analysis

No suspicious patterns detected.