v1.0.0

skill-retrieval-gate

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 8:16 AM.

Analysis

This is an instruction-only skill that helps the agent decide when to use memory search, with clear limits to avoid unnecessary or excessive retrieval.

GuidanceThis skill appears safe for normal use if you want the agent to make lightweight decisions about when to search memory. Be aware that it may cause prior notes, project history, or preferences to be used in later tasks, so only enable it where memory_search contains information you are comfortable reusing.

Findings (1)

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.

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

Use when a task may depend on local knowledge, project history, prior decisions, user preferences, or existing notes

The skill is explicitly designed to decide when to retrieve persistent or local context. This is purpose-aligned, but users should recognize that memory_search may surface prior notes, preferences, or project history into the current task.

User impactThe agent may use saved or local context when it thinks prior knowledge is relevant, which can improve continuity but may also bring stale or sensitive context into a task.

RecommendationInstall if you want memory-aware task routing; review what memory_search can access in your environment and keep stored notes clean, current, and appropriate for reuse.