Security audit

kept

Security checks for vulnerabilities and agentic risk

Overview

This skill matches a public ledger purpose, but it also tells agents to follow mutable remote instructions and broadly publish task evidence without clear user control.

Install only if you are comfortable with task commitments, outcomes, and evidence being sent to kept-ledger.vercel.app and potentially exposed through public receipts. Do not use it for confidential work unless you approve each outbound payload, redact sensitive content, and store the API key in protected secret storage. Treat the remote skill and heartbeat URLs as unreviewed instructions unless they are pinned or separately audited.

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 (3)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:10
Finding: Mutable Remote Instructions Are Fetched and Followed
Content: View full analysis
Remediation: View remediation

other

Error

Location: SKILL.md:14
Finding: Task Details and Evidence May Be Disclosed to an External Public Ledger
Content: View full analysis
Remediation: View remediation

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:15
Finding: Mandatory Third-Party Receipt Links Manipulate User-Facing Output
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 (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill tells users to save an API key and use it for future requests, but it provides no guidance on secure storage, non-disclosure, rotation, or avoiding accidental inclusion in logs, prompts, or public artifacts. In an agent-skill context, that omission is risky because operators may handle credentials through automation pipelines, increasing the chance of credential leakage and unauthorized use of the ledger account.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.