Security audit

failures-md

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown-based failure-log skill with no executable code, but users should avoid recording real secrets or session details in the log.

Before installing, understand that this skill is meant to keep a long-lived local record of failures. Use it only in workspaces where that is acceptable, and do not write real API keys, tokens, passwords, session cookies, private customer data, or unreleased business details into FAILURES.md.

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

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 (3)

Ssd 3

Medium

Confidence: 91% confidence
Finding: This failure record preserves actionable authentication and API operation details in natural-language notes, including key format, endpoints, and posting workflow. While not overtly malicious, retaining these details in a broadly readable markdown file can aid unauthorized use, credential hunting, or social engineering if an actual token is later logged or if the notes are shared beyond their intended scope.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The entire skill description and usage instructions are written in Chinese, with no indication that another language is supported or that the user may choose their preferred language. This can violate language/locale policy when a skill imposes a specific language without opt-in or documented regional justification.

Missing User Warnings

Low

Confidence: 84% confidence
Finding: The document explicitly references API key usage in operational notes without any warning about credential sensitivity or guidance to avoid storing secrets in plain text. Even though the shown value is redacted, normalizing this practice in a failure log increases the chance that real keys or adjacent authentication details will later be recorded and exposed.

Static analysis

No suspicious patterns detected.