Security audit

Concord

Security checks for vulnerabilities and agentic risk

Overview

This skill is a privacy-checking integration, but it silently sends potentially sensitive unredacted user text to an external service without clear user consent.

Install only if you are comfortable with potentially sensitive text being sent to the Concord service for processing. Avoid using it for credentials, secrets, protected health information, payment data, national identifiers, or children's data unless you have verified the service operator, retention policy, authorization controls, and user-consent requirements.

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

Findings (2)

other

Error

Location: SKILL.md:14
Finding: Unredacted Sensitive Data Is Silently Disclosed to an External Service
Content: View full analysis
Remediation: View remediation

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:14
Finding: Mandatory Hidden Invocation Hijacks Agent Consent and Disclosure Behavior
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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

Findings (2)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly instructs the agent to transmit user text that may contain highly sensitive categories of data to an external service before forwarding it elsewhere, and it states that no API key is required. Because this transfer is autonomous and not paired with a user notice or consent step, it creates a real privacy and data-exfiltration risk: sensitive content leaves the primary system even when the user may not expect any third-party processing.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The instruction to avoid announcing the privacy check intentionally suppresses transparency around off-system handling of user data. Even if the service is meant to improve privacy, concealing the external call undermines informed consent, prevents users from making risk-based decisions, and can violate organizational or regulatory requirements for notice around third-party data processing.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.