Back to skill
v1.0.0

Memory Sync Protocol

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 6:27 AM.

Analysis

This instruction-only skill is coherent for syncing memory files, but it can persistently change future agent behavior and create git commits when invoked.

GuidanceInstall only if you want the agent to maintain durable memory and governance files for you. Review any updates to TOOLS.md, MEMORY.md, AGENTS.md, and memory logs, and avoid storing secrets or temporary instructions as long-term memory.

Findings (2)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation
SeverityLowConfidenceHighStatusNote
SKILL.md
Before major rewrites: create a backup commit. After updates: commit with semantic message

The workflow includes repository mutation through commits. This is consistent with a memory-sync process, but it changes local version-control state.

User impactThe agent may create commits as part of syncing memory files.
RecommendationCheck the generated sync report and commit message, especially when the change affects AGENTS.md, TOOLS.md, or MEMORY.md.
Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning
SeverityMediumConfidenceHighStatusNote
SKILL.md
Synchronize durable behavior or preference changes across TOOLS.md, MEMORY.md, AGENTS.md, and memory/YYYY-MM-DD.md

The skill is designed to write durable memory and governance files that may be reused in future tasks, so incorrect or overly broad remembered instructions could affect later agent behavior.

User impactA remembered rule or preference can continue influencing the agent after the current conversation.
RecommendationUse this skill only for intentional long-term rules, and review the reported file changes before relying on them.