Back to skill

Security audit

Find Job UK

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a Gumtree job-search helper, but its listing script can fetch arbitrary URLs and its install path adds persistent/global components, so users should review it before installing.

Install only if you are comfortable with a global bb-browser dependency and persistent adapter files. Prefer pinning the bb-browser version, reviewing the bundled JavaScript, and restricting listing lookups to Gumtree URLs or running the tool in a constrained environment.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
bb-sites/gumtree/listing.js:65
Finding

Unrestricted Absolute URL Fetch Enables Server-Side Request Forgery

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:25
Finding

Unpinned Global npm Dependency Creates a Supply-Chain Execution Risk

Content
View full analysis
Remediation
View remediation
``` 2. Document the expected npm package integrity hash and verify the downloaded artifact. 3. Prefer a project-local dependency recorded in `package.json` and a committed lockfile over a global installation. 4. Use `npm ci` with the reviewed lockfile where practical. 5. Disable lifecycle scripts with `--ignore-scripts` if bb-browser does not require them. 6. Review package provenance, publisher identity, release signatures, transitive dependencies, and lifecycle scripts before updating the pinned version. 7. Run the tool under a dedicated, least-privileged account or sandbox with restricted filesystem and network access. 8. Establish a controlled dependency-update process in which each new version is reviewed before the documentation is changed. ]]>
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill claims specialization around jobs and part-time vacancies, but the analyzer indicates the underlying capability supports arbitrary classifieds queries and does not use or enforce a dedicated hours parameter. This kind of description-behavior mismatch can cause unsafe overtrust and policy bypass, since operators may allow the skill under the assumption it cannot access non-job content when it actually can.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill claims specialization around jobs and part-time vacancies, but the analyzer indicates the underlying capability supports arbitrary classifieds queries and does not use or enforce a dedicated hours parameter. This kind of description-behavior mismatch can cause unsafe overtrust and policy bypass, since operators may allow the skill under the assumption it cannot access non-job content when it actually can.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill requires and instructs use of bb-browser to perform live Gumtree queries, which is a network-capable action, yet the skill declares no explicit tool scope such as permissions or allowed-tools. Missing scope increases the chance the skill is run with broader-than-necessary capabilities and makes review harder because operators cannot tell from metadata what external access is intended.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
76% confidence
Finding

The installation instructions copy site scripts into ~/.bb-browser/sites/gumtree, creating persistent behavior that survives the current session. Persistence is risky because modified or malicious scraper code placed in a user-scoped plugin directory can continue to run on future invocations, and the skill does not describe integrity verification or cleanup.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

bash
mkdir -p ~/.bb-browser/sites/gumtree
cp bb-sites/gumtree/search.js ~/.bb-browser/sites/gumtree/search.js
cp bb-sites/gumtree/listing.js ~/.bb-browser/sites/gumtree/listing.js

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The request hard-codes Accept-Language: en-GB,en;q=0.9, which imposes a specific language/locale preference. Under the policy, locale constraints should be optional or clearly justified; this file does not offer user opt-in or explain why English (UK) is required.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This code performs an HTTP request to Gumtree using user-supplied search terms and location, which transmits potentially sensitive user intent or approximate location to an external site. Within this file there is no confirmation prompt, logging, comment, or docstring warning the user that their inputs will be sent over the network.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The request hard-codes the Accept-Language header to 'en-GB,en;q=0.9', which imposes a specific language/locale preference regardless of the user's settings or choice. This is a natural-language policy concern because the skill does not offer any language or locale opt-in, override, or documented justification for the constraint.

Content

No source excerpt is available for this finding.