Skillv1.0.0

ClawScan security

Agile Toolkit · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignFeb 12, 2026, 7:32 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only Agile coaching skill whose requested resources and runtime instructions align with its stated purpose and show no signs of unexpected access, installs, or credential requests.
Guidance: This skill is instruction-only and appears coherent with its Agile coaching purpose: it doesn't request credentials, perform installs, or reference system files. Before installing, consider: (1) the publisher identity is minimal (no homepage or author verification) — if provenance matters for your org, verify the author externally; (2) any sensitive project details you paste into the chat will be included in responses and could be stored by the agent platform — avoid pasting secrets; (3) the skill can be invoked autonomously by the agent (normal default) — if you want tighter control, disable autonomous invocation in agent settings. Other than those operational/privacy considerations, there are no technical red flags.

Purpose & Capability: okThe name, README, and SKILL.md all describe Agile coaching (retros, planning, user stories, standups, metrics). The skill requires no binaries, env vars, or config paths — which is proportionate for a text-only coaching assistant.
Instruction Scope: okSKILL.md contains detailed facilitation scripts, templates, question prompts, and calculation guidance. It does not instruct the agent to read files, access system state, call external endpoints, or collect unrelated data. The instructions stay within the domain of Agile coaching and facilitation.
Install Mechanism: okThere is no install specification and no code files — the skill is instruction-only, so nothing is written to disk or downloaded. This is the lowest-risk installation profile.
Credentials: okThe skill declares no required environment variables, credentials, or config paths. There is no apparent need for secrets or external service access for the described functionality.
Persistence & Privilege: okalways:false and default autonomous invocation are used. The skill does not request permanent presence or access to other skills' configurations. Autonomous invocation is normal; there is no 'always:true' privilege escalation or other persistence asked for.