Security audit

running tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local running log that reads and updates its own runs.md file for workout tracking.

Before installing, understand that the skill keeps a local running history in runs.md and may use running-related messages to offer logging or analysis. Confirm details before allowing it to append a workout entry if your message was ambiguous.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description includes broad triggers such as 'anything related to their running data' and examples like 'just finished a run', which can cause the skill to activate on loosely related or ambiguous user messages. Over-broad activation increases the chance of unintended file reads/writes to runs.md or the model steering into run-logging behavior when the user did not explicitly request it.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.