Back to skill

Security audit

Brd Browser Debug

Security checks for vulnerabilities and agentic risk

Overview

This Bright Data debugging skill is coherent overall, but it can use an API key to enumerate recent browser sessions from broad troubleshooting cues.

Install only if you want an agent to query your Bright Data browser session history. Prefer invoking it explicitly with a session ID, zone, target domain, or date range, and avoid letting generic scraper failures trigger a broad recent-session review.

Vulnerability Patterns
  • 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
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is user-invocable and also advertises broad auto-trigger phrases like 'scraper not working', 'script didn't work', 'found 0', and other generic failure language. Those triggers can match many unrelated conversations and cause the agent to invoke a networked diagnostic skill unnecessarily, increasing the chance of sending user-derived context such as domains, session IDs, or troubleshooting targets to an external service without sufficiently specific user intent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 34)May include surrounding context.

Start with a single call using limit=100 (the maximum) sorted by most recent:

text
GET https://api.brightdata.com/browser_sessions?limit=100&sort=timestamp&order=desc
Authorization: Bearer $BRIGHTDATA_API_KEY

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 68)May include surrounding context.

Start with a single call using limit=100 (the maximum) sorted by most recent:

text
GET https://api.brightdata.com/browser_sessions?limit=100&sort=timestamp&order=desc
Authorization: Bearer $BRIGHTDATA_API_KEY

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The auto-detect logic treats broad 'empty/unexpected results' signals as sufficient to run list-and-triage logic, and only loosely says to filter by the relevant target domain. In practice, this can cause the skill to activate on ambiguous troubleshooting conversations and fetch up to 100 recent sessions, exposing operational metadata from unrelated browsing jobs beyond what the user actually asked about.

Content

No source excerpt is available for this finding.