Security audit

Context Archive Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims: it saves user-confirmed conversation summaries as local Markdown archives and can list or reload them later.

Install only if you are comfortable with conversation summaries being saved locally under archives/. Avoid archiving sensitive secrets or private data unless you intend that summary to remain on disk, and periodically review or delete archive files you no longer need.

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 (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The trigger section lists phrases like "archive today's conversation" and "archive recent conversation" without defining boundaries for what counts as recent, what conversation scope is included, or when the skill should not activate. Because this is a markdown file and the activation guidance is open-ended with no negative examples, it could lead to unintended invocation from ordinary conversation-management requests.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The markdown explicitly states that conversations are summarized and saved as .md files, which affects user data by persisting potentially sensitive conversation content to local storage. While the feature is described functionally, there is no user-facing warning about privacy implications, retention, or that archived content will remain on disk.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill persistently writes conversation-derived summaries to archives/ and auto-creates that directory, but it never clearly warns the user that data will be stored on disk and remain accessible later. Because archived content may contain sensitive decisions, identifiers, project details, or other confidential material, this creates a real privacy and data-retention risk even though the feature is intentional.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The natural-language policy requires not forcing a specific language or locale without user opt-in. Declaring a 'Chinese-first interface' suggests the skill defaults to Chinese presentation even though users may prefer another language, and no explicit language selection step is offered here.
Content: No source excerpt is available for this finding.