Back to skill

Security audit

Meet-Pets-Friends❤️

Security checks for vulnerabilities and agentic risk

Overview

The skill is presented as pets-only, but the included code can search broader Gumtree categories and fetch non-Gumtree URLs, so it needs review before installation.

Review before installing. Use this only if you are comfortable with a bb-browser adapter that is broader than the pets-only description. Prefer a version that enforces pet categories, requires HTTPS URLs on www.gumtree.com, rejects redirects to other hosts, and pins the bb-browser dependency instead of installing the latest global package.

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:66
Finding

Unrestricted Listing URL Enables Server-Side Request Forgery

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:34
Finding

Unpinned Global Installation of a Third-Party Dependency

Content
View full analysis
Remediation
View remediation
``` 2. Verify whether lifecycle scripts are required before enabling them. Keep `--ignore-scripts` when they are unnecessary. 3. Prefer a project-local installation over a global installation to reduce system-wide impact: ```bash npm install --save-exact --ignore-scripts bb-browser@ ``` 4. Commit and verify a lockfile when the packaging model permits it. 5. Record and verify package integrity or provenance information. 6. Review the pinned package’s transitive dependencies and lifecycle scripts. 7. Define an explicit update and re-audit process instead of automatically consuming the latest release. 8. Advise users not to run the installation command with elevated privileges. ]]>
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

If the code defaults to all or permits arbitrary categories, the skill is not actually scoped to pets despite repeated claims that it is. This creates a trust-boundary problem: systems may approve or route the skill under a benign animal-welfare use case while it can in fact scrape generic classifieds, broadening data access and bypassing policy expectations.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

If the code defaults to all or permits arbitrary categories, the skill is not actually scoped to pets despite repeated claims that it is. This creates a trust-boundary problem: systems may approve or route the skill under a benign animal-welfare use case while it can in fact scrape generic classifieds, broadening data access and bypassing policy expectations.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 38)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

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The adapter accepts a caller-controlled category/search_category and defaults to all, so it is not technically restricted to pets despite the skill metadata claiming pets-only use. This creates a scope-integrity problem: higher-level systems or users may rely on the declared pet-only constraint, but the code permits searches across unrelated Gumtree categories.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

By exposing args.category || args.search_category || 'all', the skill provides a generic Gumtree search primitive rather than the narrower pet-search capability it advertises. In an agent setting, this can bypass policy or product restrictions built around the declared purpose of the skill, enabling unreviewed access to broader classified content.

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. This is a natural-language policy concern because the skill does not offer user opt-in or explain why a UK English locale is required.

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 forces an English (UK) locale regardless of the user's preferences. This is a natural-language/locale policy concern because the skill does not offer any language choice or document a justified locale restriction.

Content

No source excerpt is available for this finding.