T01 · Skill Instruction Hijacking
- Location
SKILL.md:48- Finding
Externally Retrieved Context Is Installed as a Privileged System Prompt
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent memory-service integration, but it pushes full conversations into a third-party persistent store and reuses returned memory as high-priority model instructions without enough consent, filtering, or containment guidance.
Review before installing or following the examples. Use this only where users have explicitly opted into persistent memory, redact secrets and regulated data before calling update(), avoid sending full raw conversations when narrower fields will do, keep retrieved memory outside the system prompt or mark it as untrusted context, and pin and review the SDK version used in production.
SKILL.md:48Externally Retrieved Context Is Installed as a Privileged System Prompt
SKILL.md:141Automatic Persistent Storage of Unfiltered Conversation Content Enables Memory Poisoning and Sensitive-Data Retention
SKILL.md:48Third-Party SDK Is Referenced Without a Pinned or Verifiable Version
The examples send userMessage and agentResponse to a third-party memory service without a prominent privacy warning or consent guidance. Because these payloads can contain sensitive personal, proprietary, or regulated data, implementers may unknowingly exfiltrate user content outside their primary LLM provider and store it persistently.
The skill advertises storage of inferred emotional_state and other persistent user context without a strong warning that this may constitute sensitive personal data. This increases the risk that developers deploy profiling of users' mood, stress, or sentiment without explicit consent, proper access controls, or compliance review, leading to privacy harm and regulatory exposure.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
# Inject
POST https://api.threadline.to/api/inject
Authorization: Bearer YOUR_API_KEY
{ "userId": "user_123", "basePrompt": "You are a helpful assistant." }
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
# Inject
POST https://api.threadline.to/api/inject
Authorization: Bearer YOUR_API_KEY
{ "userId": "user_123", "basePrompt": "You are a helpful assistant." }
The update REST example explicitly sends userMessage and agentResponse to an external service for persistent storage. In the context of a memory product that stores cross-session context 'forever' and includes sensitive inferred scopes, this materially increases privacy and data leakage risk if developers forward raw conversations without redaction, consent, or minimization.
{ "userId": "user_123", "basePrompt": "You are a helpful assistant." }
POST https://api.threadline.to/api/update Authorization: Bearer YOUR_API_KEY { "userId": "user_123", "userMessage": "...", "agentResponse": "..." }