v1.0.0

unCAGd

BenignClawScan verdict for this skill. Analyzed May 2, 2026, 9:21 PM.

Analysis

This is a coherent project-memory skill, but users should notice that it persists decisions and references an external MCP/package implementation not included in the reviewed artifacts.

GuidanceThis skill appears purpose-aligned for validated project decision memory. Before installing, confirm you trust the referenced MCP package/runtime, understand where memory is stored, and review or approve decisions before they become durable 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.

Agentic Supply Chain Vulnerabilities

SeverityLowConfidenceMediumStatusNote

_meta.json

"package": "@uncagd/openclaw-cag-memory", "mcpServer": { "name": "uncagd-memory", "command": "uncagd", "args": ["start"] }

The metadata references an external package and MCP server command, but no implementation code or install specification is included in the reviewed artifacts.

User impactThe reviewed instructions look coherent, but this review cannot verify what the external MCP package actually does at runtime.

RecommendationInstall only from a trusted source, verify the package provenance/version, and review the MCP server implementation before relying on it for persistent project memory.

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

SeverityLowConfidenceHighStatusNote

SKILL.md

Before planning or editing code, call `cag.retrieve`... Use retrieved decisions as constraints, not as proof of current code state.

The skill intentionally retrieves persistent project decisions that can influence future planning and code work, while also warning not to over-trust that memory.

User impactIncorrect, stale, or imported memory could steer future project decisions, even though the skill includes validation safeguards.

RecommendationReview validated memories periodically, validate only trusted decisions, and be careful when importing or exporting memory between workspaces.