Security audit

Podpoint

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to only check and watch public Pod Point charger availability, with a bounded-use caution around polling inputs.

Reasonable to install for checking a known Pod Point pod, but prefer explicit pod IDs and ensure the host enforces finite, sensible interval and timeout limits before allowing long watch runs.

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

Warning

Location: index.js:65
Finding: Non-finite timing values can cause unbounded rapid polling
Content: View full analysis
Remediation: View remediation
max) { throw new RangeError(`${name} must be between ${min} and ${max}`); } return candidate; } async function podpoint_watch({ podId, intervalSeconds = 30, timeoutSeconds = 900 }) { const interval = validateFiniteNumber( intervalSeconds, "intervalSeconds", 5, 300, 30 ); const timeout = validateFiniteNumber( timeoutSeconds, "timeoutSeconds", interval, 3600, 900 ); const maximumIterations = Math.ceil(timeout / interval); let iterations = 0; while ( Date.now() - started < timeout * 1000 && iterations++ < maximumIterations ) { // Polling logic } } ``` If accepting numeric strings is required, convert them first and then apply `Number.isFinite()` and the same range checks. Runtime validation should remain in place even when the host claims to enforce the JSON schema. ]]>

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

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The example trigger "Monitor this Pod Point" is relatively broad and does not specify the exact action scope, duration, or required identifier. In conversational contexts, this could cause unintended invocation because it lacks constraints such as a pod ID or explicit monitoring mode.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.