T01 · Skill Instruction Hijacking
- Location
SKILL.md:100- Finding
Autonomous Modification of Agent Behavior and Persistent Memory
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 100-105
Vulnerability Type: Agent instruction hijacking and persistent memory poisoning
Risk Level: HighVulnerable Code:
text **CAN modify without asking:** - Skills and capabilities - Memory and knowledge - Reasoning patterns - Response formats - Efficiency optimizationsTechnical Analysis
The Skill explicitly authorizes itself to modify memory, knowledge, reasoning patterns, response formats, and capabilities without obtaining user approval. These resources form part of the Agent's behavioral control plane rather than ordinary task output.
If an Agent interprets these instructions as authority to perform modifications, the Skill can replace or weaken behavioral rules during the current session. Changes written into long-term memory or other persistent state may continue influencing subsequent sessions. Although the repository contains documentation and illustrative pseudocode rather than an executable implementation, the content of
SKILL.mdis itself operationally relevant because Agent skills are instruction-driven.The issue matches both
T01: Skill Instruction Hijacking, because loading and following the Skill can alter current goals or behavioral constraints, andT02: Agent Memory Poisoning, because the Skill expressly permits unsupervised modification of persistent memory and knowledge.Attack Path
- A user or automated workflow loads the self-evolution Skill.
- The Agent treats the “CAN modify without asking” section as delegated authority.
- An evolution cycle selects memory, reasoning rules, response behavior, or another Skill as its modification target.
- The Agent writes new behavioral content without presenting the exact change for user approval.
- Modified reasoning or response rules affect the current session.
- If written to persistent memory or Skill files, the altered rules are loaded again a ...[truncated 873 chars]
- Remediation
View remediation
Remediation Suggestions
- Remove blanket permission to modify memory, reasoning patterns, response formats, capabilities, or other Skills.
- Require explicit, per-change user approval before modifying any persistent or behavioral state.
- Present the target file, exact diff, justification, security impact, and rollback procedure before approval.
- Prohibit modification of system prompts, safety policies, tool permissions, approval rules, and security controls.
- Restrict writes to a dedicated Skill-owned workspace through an allowlist and deny writes outside that directory.
- Treat conversation content, logs, memory, and generated research as untrusted input that cannot grant new authority.
- Validate proposed changes against immutable security policies enforced outside the self-modifying component.
- Use version-controlled changes, integrity checks, immutable audit logs, and tested rollback procedures.
- Require separate approval for every persistent memory update rather than treating approval of an evolution cycle as approval of all resulting writes.
