Back to skill

Security audit

article-writing

Security checks for vulnerabilities and agentic risk

Overview

This Chinese writing skill is mostly coherent, but it tells the agent to keep rewriting its own installed skill instructions after writing tasks, which can persist unchecked changes into future sessions.

Review SKILL.md before installing. Use it only if you want a Chinese article-writing skill that may trigger on broad writing and editing terms. Keep the installed skill directory read-only during normal use, or require explicit human review of any proposed changes to SKILL.md before accepting them.

Vulnerability Patterns
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • 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 (1)

T02 · Agent Memory Poisoning

Warning
Location
SKILL.md:62
Finding

Persistent Skill Self-Modification Can Poison Future Agent Behavior

Content
View full analysis
## 4. Update Protocol (Living Document) > This Skill is a living document: **after each article-writing or editing task produces new experience, append or revise the corresponding section, increment the version, and add an entry to the changelog below**. Organize experience by topic under the sections above; do not create duplicate entries for the same mistake. The snippet is an English translation of the complete instruction at the identified location. ### Technical Analysis The Skill directs the agent to modify its own persistent instruction file after writing or editing tasks. Lessons derived from user submissions or other untrusted article content may therefore be promoted into durable operating instructions without validation, isolation, or human approval. This crosses a security boundary between transient task content and persistent agent state. An attacker could craft an article, editing request, or feedback intended to be interpreted as a reusable lesson. If the agent follows the update protocol and has write access to the Skill directory, that content could be incorporated into `SKILL.md` and loaded automatically in later sessions. No executable scripts, credential access, privilege-escalation logic, remote payload execution, or operating-system persistence were identified. The risk is confined to persistent modification of agent guidance and is conditional on the agent having permission to edit the Skill file. ### Attack Path 1. The agent loads `SKILL.md` and accepts its living-document update protocol. 2. An attacker supplies crafted article content or feedback containing a misleading rule presented as a generally useful writing lesson. 3. During the task, the agent treats the attacker-controlled material as newly learned ...[truncated 1070 chars]
Remediation
View remediation
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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes very generic Chinese terms such as “文章”, “润色”, and “改写”, which are common in ordinary conversations and many unrelated tasks. This can cause the skill to activate outside its intended scope, injecting its instructions into unrelated workflows and influencing outputs without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language description frames the skill as a Chinese article-writing resource and uses Chinese-only trigger wording, but it does not state that this language limitation is optional or user-selected. Under the language/locale policy, a fixed language should be offered as a choice or clearly justified as a locale-specific tool.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README instructs users to copy the skill into the agent's skills directory, which enables automatic invocation based on trigger keywords, but it does not clearly warn that this modifies agent behavior. That can lead users to install and trust behavior-changing prompt content without informed consent or review, increasing the risk of unexpected prompt injection or misuse if the skill content is later changed or expanded.

Content

No source excerpt is available for this finding.