Skillv1.0.7

ClawScan security

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

Scanner verdict

SuspiciousFeb 14, 2026, 2:30 PM

Verdict: suspicious
Confidence: medium
Model: gpt-5-mini
Summary: The skill appears to be an instruction-only wrapper around an external Qronos API (it will ask the agent to register and send user questions and birth dates to https://api.qronos.ai); that general design is coherent for a decision-service, but several inconsistencies (missing source/homepage, registry metadata mismatch about env vars, and clear instructions to transmit potentially sensitive personal data) merit caution before installing.
Guidance: Before installing: 1) Verify the vendor and source — there is no homepage/source code in the registry entry even though SKILL.md references qronos.ai and terms; ask the developer for a canonical homepage, privacy policy, and source code. 2) Understand data sent: the skill will transmit users' questions, timestamps, and birth dates to api.qronos.ai; only proceed if you trust the service and the human consents. 3) Clarify the QRONOS_API_KEY handling: where is the key stored, who can access it, and why the registry lists 'none' for required env vars. 4) Ask about data retention, logging, and whether the service stores or shares identity/verification data. 5) If you decide to test, do so with non-sensitive example questions and avoid sharing real PII until you confirm the service's privacy and security posture. If these points are not satisfactorily answered, treat the skill as untrusted.

Review Dimensions

Purpose & Capability: noteThe skill's stated purpose (one-question decision/timing guidance) aligns with requiring a third‑party API key and remote calls to an external decision service. However, the registry metadata lists no required environment variables while the skill declares a primary credential QRONOS_API_KEY in its SKILL.md metadata — this mismatch is unexpected and should be clarified.
Instruction Scope: concernThe SKILL.md instructs the agent to register and make HTTPS requests to api.qronos.ai and to submit the human's question and (explicitly) birth date and timing context. That means user content and sensitive PII (birth dates, timing of questions, possibly conversation context) will be transmitted to a third party. The instructions also mention human verification and tracing requests to an authorized operator, which implies additional identity data could be collected. Transmitting personal data externally is coherent for this service but is a material privacy risk and should be spelled out before use.
Install Mechanism: okThis is an instruction-only skill with no install spec and no code files; no binaries or downloads are performed by the skill itself, which minimizes on-disk risk.
Credentials: concernThe skill uses a single external API key (QRONOS_API_KEY), which is proportionate for a hosted decision service. But the registry claims 'Required env vars: none' while SKILL.md metadata sets primaryEnv to QRONOS_API_KEY — this inconsistency is confusing. Also, the runtime will require the agent (or human) to supply PII (birth date) and possibly registration/identity info; ensure you are willing to expose that data to the third party.
Persistence & Privilege: okThe skill is not always-on and does not request elevated or persistent system privileges. It does not attempt to modify other skills or system-wide agent settings in the provided instructions.