Security audit

Sentiment Score

Security checks for vulnerabilities and agentic risk

Overview

The skill does sentiment scoring as advertised, but its HTTP mode can expose an unauthenticated endpoint that spends the operator's OpenAI API quota.

Review the HTTP/MCP mode before installing or running it. Use the CLI mode for local-only use, or change the server to bind to localhost and put any remote deployment behind authentication, request-size limits, rate limits, and OpenAI spending controls. Do not submit sensitive text unless you are comfortable sending it to OpenAI.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Error

Location: pipeline-mcp.yaml:5
Finding: Unauthenticated Network Endpoint Permits Abuse of the Operator's OpenAI API Account
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The pipeline forwards raw stdin content directly to an external OpenAI API as the user message, which can expose sensitive data entered at the CLI to a third-party service. Because this file contains no notice, consent mechanism, redaction, or input restrictions, operators may unknowingly transmit secrets, personal data, or proprietary content off-host.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The pipeline forwards arbitrary user-supplied text to the external OpenAI API, and this file shows no disclosure, consent, or data-handling controls around that transfer. This creates a real privacy and compliance risk because users may submit sensitive content that is transmitted to a third party without clear warning or minimization.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: This manifest identifies the skill name and type but does not describe when it should be invoked or what specific user phrases or contexts should activate it. For manifest files, missing specificity on trigger scope can lead to ambiguous or overly broad invocation behavior if activation is inferred elsewhere.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.