Back to skill
Skillv1.0.0
ClawScan security
Lore · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 11, 2026, 9:10 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's instructions, scope, and requirements are internally consistent with a knowledge-repository integration: it only contains guidance to use existing Lore tools (ingest/search/research/get_source/retain), requests no unexpected credentials or installs, and does not try to access unrelated system resources.
- Guidance
- This skill is coherent with its stated purpose and requests nothing unexpected, but be mindful of the following before installing: 1) It expects your agent to have connectors (Slack, Notion, GitHub, email) or MCP tooling to pull content — ensure those connectors have appropriate scopes and you trust them. 2) Ingesting can store sensitive content in the Lore repository; confirm retention and access policies and obtain consent before ingesting private data. 3) Although the skill itself requests no credentials or installs, review the permissions of any external integrations the agent will use.
Review Dimensions
- Purpose & Capability
- okThe name/description (search and ingest knowledge from a research repository) matches the SKILL.md instructions which describe when/how to use ingest/search/research/get_source/retain. No unrelated binaries, env vars, or installs are requested.
- Instruction Scope
- noteInstructions stay within the repository use-case (ingest/search/retain/research). They explicitly recommend ingesting content from Slack, Notion, GitHub, email, etc.—which is appropriate for a knowledge base but means the agent will handle potentially sensitive content if those connectors exist. The SKILL.md does not instruct the agent to read arbitrary local files or undeclared environment variables.
- Install Mechanism
- okNo install spec and no code files — instruction-only skill. This minimizes on-disk risk.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. The guidance to use external connectors is reasonable for the stated purpose; there are no unexplained secret requests.
- Persistence & Privilege
- okalways:false and user-invocable:false. disable-model-invocation:false (normal); the skill does not request permanent presence or to modify other skills or system settings.