Security audit

Session Brief

Security checks for vulnerabilities and agentic risk

Overview

This skill only helps summarize the current chat in-place and does not request hidden access, persistence, or external execution.

Installers should understand that invoking this skill may cause the agent to recap sensitive details already present in the chat, but the skill explicitly tells the agent not to include secrets, tokens, private credentials, or unnecessary personal data.

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

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The description says to use the skill when the user 'wants the current conversation summarized for reference' or 'says the chat is bloated or slow,' which are broad natural-language situations rather than narrowly scoped trigger phrases. Without clearer boundaries or exclusion examples, this could cause unintended activation in ordinary conversation about summaries or chat performance.
Content: No source excerpt is available for this finding.