Back to skill
Skillv1.0.1
ClawScan security
Repository Discovery · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 24, 2026, 9:10 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's instructions, requested resources, and scope are consistent with its stated purpose of exploring and documenting a GitHub repository; nothing requested appears disproportionate or unrelated.
- Guidance
- This skill is coherent and appropriate for documenting a repository. Before using it, confirm which repository the agent will access and whether it is allowed to view any private repos. Be aware the agent will look for config and .env files and may encounter secrets; if you do not want secret values recorded or transmitted, either remove/redact them in the repo or instruct the agent (or your agent runtime) to only record variable names and not values. Also review any repository .github/* agent instructions it will prioritize, since those files can change agent behavior.
Review Dimensions
- Purpose & Capability
- okThe name/description match the SKILL.md: the instructions focus on scanning repository files (README, package manifests, Dockerfiles, .github configs, etc.) and producing a structured REPO_DISCOVERY.md. No unrelated binaries, installs, or external services are required.
- Instruction Scope
- noteInstructions appropriately direct the agent to inspect repository files and metadata. They explicitly include looking for configuration files and .env/.env.example to document required env vars and API endpoints — this is reasonable for repo discovery but means the agent will encounter secrets and credentials if present. The SKILL.md does not instruct the agent to read system-wide files outside the repo or to transmit data to unexpected external endpoints.
- Install Mechanism
- okThis is an instruction-only skill with no install spec and no code files, so nothing is written to disk or installed by the skill itself.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. The only data it asks the agent to inspect is repository-local (dependency files, .env in repo, config directories), which is proportional to its purpose.
- Persistence & Privilege
- okalways is false and the skill does not request persistent presence or modify other skills. It relies on normal agent invocation behavior and does not ask for elevated agent-wide privileges.