Security audit

rt-attention-analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill locally analyzes reaction-time CSV data and writes reports, with a spreadsheet-safety caveat for exported CSV files.

Install only if you are comfortable running local Python scripts on your RT datasets. Treat generated CSV reports as containing untrusted input data; avoid opening them in spreadsheets with formula execution enabled when the source CSV is not fully trusted.

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 (2)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/rt_trigger.py:142
Finding: CSV Formula Injection in Triggered Trial Export
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/rt_analyze.py:334
Finding: CSV Formula Injection Through Participant Identifiers in Metrics Export
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: The code accurately implements part of the declared purpose: real-time RT triggering using trailing averages, cumulative mean/SD, and optional correctness/frequency gating. However, the description substantially overstates functionality by claiming lapse detection, RT variability analysis, bootstrap/effect-size statistics, and plotting with trigger markers, none of which are present in this code chunk. The primary purpose is aligned with sustained-attention RT triggering, but the implemented capabilities are materially narrower than described.
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.