Back to skill
Skillv1.0.0
ClawScan security
meeting-agenda-creator · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 20, 2026, 10:32 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only meeting agenda generator whose declared purpose, runtime instructions, and resource requirements are internally consistent and do not request credentials or install code.
- Guidance
- This skill appears low-risk: it is instruction-only, asks for no secrets, and matches its stated purpose. Before using, avoid pasting confidential documents into the prompt (the skill can accept 'relevant documents' as context but will not fetch them automatically). If you plan to use it in automated/agentic workflows, be aware the agent could invoke the skill autonomously—ensure your agent's overall permissions and any attached data policies are appropriate. Finally, review generated agendas for accuracy and sensitive content before distribution.
Review Dimensions
- Purpose & Capability
- okName, description, and SKILL.md all align: the skill produces meeting agendas, templates, time allocation, and role assignments. No unrelated binaries, env vars, or config paths are requested.
- Instruction Scope
- okSKILL.md contains only user-facing guidance and example inputs/outputs. It does not instruct the agent to read system files, access environment variables, call external endpoints, or exfiltrate data. It does mention 'relevant documents or reports' as user-supplied context but does not direct automatic retrieval of those files.
- Install Mechanism
- okNo install spec or code is present (instruction-only). Nothing will be downloaded or written to disk by an installer.
- Credentials
- okNo credentials, API keys, or environment variables are required. There is no disproportionate access requested for the skill's stated purpose.
- Persistence & Privilege
- okalways is false and the skill does not request elevated persistence or permission to modify other skills or system-wide settings. Autonomous invocation (model invocation) is allowed by default, which is normal for skills and not a concern here.
