Security audit

brand-listener

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed public social-listening helper that installs and pairs a ClawLink plugin, then uses paid read-only public data tools.

Before installing, confirm you are comfortable pairing with ClawLink, spending ClawLink credit per call, and sending brand or topic search queries through its public-data tools. Avoid using it for private accounts or sensitive non-public investigations.

A.I.G

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

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The manifest and documentation frame this skill as a read-only brand-monitoring tool for public social data. Line L166 instructs use of clawlink_report_issue, which contacts the ClawLink team and submits a report rather than retrieving social-listening data, adding an operational support capability not justified by the stated purpose.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.