Org Memory Curator

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 8:14 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed organizational memory curator, with no executable code, but users should control what gets archived because it can persist chat and project information.

Install only if this is meant for a Chinese-language Team Alpha organizational memory workflow. Before archiving, ensure the user or organization approves long-term storage, redact secrets and personal data, and verify the target memory paths are correct.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (8)

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The skill advertises itself for use whenever any agent needs to decide whether information is worth preserving in long-term memory, which is a very broad trigger that can match many ordinary workflows. Broad activation increases the chance that sensitive or irrelevant user/project content is routed into archival logic without a narrowly scoped user intent check, leading to over-collection and inappropriate persistence.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill is designed to archive chat content, meeting notes, user clarifications, and documents into long-term organizational memory, but it does not require any explicit warning, consent, or privacy review before persistence. In this context, the absence of retention and sensitivity guardrails is dangerous because these sources commonly contain personal data, confidential discussions, access details, or other material that should not be durably stored.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The Chinese activation text states that the skill should be used when any agent needs to deposit project progress, meeting notes, chat content, user clarifications, or markdown into organizational memory. This creates the same overbroad invocation risk in operational language, making accidental archival of routine conversations or sensitive content more likely.

Natural-Language Policy Violations

Medium

• Confidence: 96% confidence
• Finding: The short description is written only in Chinese, which imposes a specific language choice in user-facing metadata. There is no indication that the skill is region-specific or that users can choose a different language, so this appears to violate the language/locale policy constraint.

Natural-Language Policy Violations

Medium

• Confidence: 97% confidence
• Finding: The entire skill guidance is written in Chinese and includes a fixed Chinese return string, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy, language constraints should be opt-in or clearly justified when region-specific.

Natural-Language Policy Violations

Medium

• Confidence: 93% confidence
• Finding: This markdown file presents all routing instructions in Chinese and does not indicate that the user may choose another language or that the Chinese-only constraint is required for a specific regional or organizational reason. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy concern.

Natural-Language Policy Violations

Medium

• Confidence: 93% confidence
• Finding: The entire template prescribes Chinese-language headings and fixed Chinese output phrases such as the mandatory response at L020-L021, which imposes a specific language on skill output. There is no indication that the user may choose another language or that the Chinese-only constraint is justified by a documented region-specific requirement.

Natural-Language Policy Violations

Low

• Confidence: 87% confidence
• Finding: The natural-language operating instructions are presented only in Chinese, which can impose a language constraint on users or agents who do not operate in that language. The file does not offer an alternative language, opt-in choice, or explain that the skill is intentionally limited to a Chinese-language environment.