T02 · Agent Memory Poisoning
- Location
SKILL.md:72- Finding
Persistent Agent Guidance Can Be Modified Without Mandatory User Approval
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 72-81
Vulnerability Type:T02: Agent Memory Poisoning
Risk Level: MediumRelevant instruction excerpt — faithful English translation of the reviewed Markdown:
markdown ### Phase C: Register in the Skill Index Add the new Skill to `skills/quick-reference.md` if it exists, or declare it in the Skill hierarchy in `SOUL.md`. ### Phase D: Continuous Iteration Every time this Skill is used: - If a problem is found, update `SKILL.md` - If a new scenario is found, extend `SKILL.md` - If a better solution is found, rewrite the corresponding sectionTechnical Analysis
The Skill instructs the agent to write generated guidance into persistent files, including
skills/quick-reference.md, otherSKILL.mdfiles, and particularlySOUL.md. These files may influence behavior in later tasks or sessions.The workflow does not require explicit user confirmation, trusted-source validation, content sanitization, or review of a proposed diff before persistence. Because the decision to preserve a pattern is based on task content and the agent's assessment, untrusted instructions presented during an ordinary task could be misclassified as reusable guidance and stored for future use.
This is a memory-poisoning risk rather than operating-system persistence: the package does not install services, scheduled tasks, executable hooks, or startup components. No executable code, remote payload retrieval, dependency installation, credential access, or network behavior was found.
Attack Path
- An attacker supplies task content containing a seemingly reusable workflow with embedded hostile or policy-altering instructions.
- The agent completes the task and evaluates the workflow under the Skill's broad reuse criteria.
- The agent decides that the attacker-influenced workflow should be preserved.
- Following Phase C, the agent registers the genera ...[truncated 857 chars]
- Remediation
View remediation
Remediation Suggestions
- Require explicit user approval before creating, registering, extending, or rewriting any persistent Skill content.
- Do not permit this workflow to modify
SOUL.md; use a dedicated, narrowly scoped Skill registry instead. - Generate and display a complete diff before applying any persistent change.
- Record the source and trust level of proposed reusable guidance.
- Reject content containing instruction overrides, credential requests, unrelated tool commands, external payload retrieval, or attempts to weaken security controls.
- Separate untrusted task data from agent instructions and ensure copied examples cannot become executable directives.
- Apply least-privilege filesystem permissions so the Skill can write only to an approved staging directory.
- Require human review before promoting staged content into an active Skill index or other automatically loaded instruction file.
- Maintain version history and provide a rollback mechanism for all persisted Skill changes.
