Skillv1.0.0

ClawScan security

德胧调研报告技能v3 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

SuspiciousApr 20, 2026, 8:19 PM

Verdict: suspicious
Confidence: medium
Model: gpt-5-mini
Summary: Instruction-only research-report skill is functionally coherent and low-risk in behavior, but packaging metadata mismatches (owner/slug/version) create provenance concerns that warrant caution before installing.
Guidance: This skill's content aligns with its stated purpose and is low-risk because it's instruction-only and requests no credentials. However, the package metadata is inconsistent: registry owner ID/slug/version differ from values inside _meta.json and SKILL.md. That mismatch can indicate sloppy publishing or problems with provenance. Before installing: 1) Verify the skill's publisher identity (owner ID and homepage) and prefer skills with a clear homepage or trusted publisher. 2) Ask the publisher which version is authoritative and why metadata differs. 3) Test the skill in a restricted environment first and avoid feeding proprietary or sensitive data to it until provenance is confirmed. 4) When the skill fetches external sources during use, review and verify citations and original sources rather than relying solely on the skill's summaries. If you can't confirm the owner or source, exercise caution or choose a skill from a verified provider.

Purpose & Capability: noteThe SKILL.md content (frameworks, methodology, writing and sourcing guidance) matches the described purpose of producing industry research reports. However, registry metadata (owner ID, slug, and published version) does not match the _meta.json and in-file metadata, which is an inconsistency in provenance and packaging.
Instruction Scope: okRuntime instructions stay within the stated purpose: gathering public research, structuring analysis, drafting, and quality-review steps. The skill asks the agent to 'search for recent industry reports and market data' but does not prescribe reading unrelated system files, accessing secrets, or sending data to external endpoints other than generally fetching public sources.
Install Mechanism: okNo install spec and no code files are included (instruction-only). This minimizes filesystem/execution risk — nothing is downloaded or written by the skill itself.
Credentials: okThe skill declares no required environment variables, credentials, or config paths. The instructions do not reference hidden env vars or secrets. Requesting no secrets is proportionate to its stated functionality.
Persistence & Privilege: okalways:false and default autonomous invocation are used (normal). The skill does not request persistent installation or modification of other skills or system-wide settings.