Red Team Verificator
PassAudited by ClawScan on May 2, 2026.
Overview
This is an instruction-only red-team review skill with no code, install steps, credentials, or persistence, but it is intentionally harsh and should be treated as adversarial advice rather than balanced guidance.
This skill appears safe to install from a technical security perspective. Expect it to produce a deliberately skeptical red-team critique; use its conclusions as a challenge to your assumptions, not as an objective final verdict.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The assistant may strongly discourage ideas even when a more balanced business analysis would leave room for uncertainty.
The skill openly instructs the agent to be highly adversarial and pessimistic. This is aligned with a red-team verifier role, but it can make the output feel more authoritative or negative than a neutral review.
«Лучше убить 10 хороших идей, чем пропустить 1 плохую»; «НЕ МЯГЧАЙ — плохая идея = убить быстро»
Use this skill as a stress-test or second opinion, not as the sole basis for investment, product, or coding decisions.
There is little technical supply-chain exposure here, but users cannot independently inspect an external project homepage or source repository from the metadata.
The publisher provenance is limited. The risk is low because the skill is instruction-only and has no installable code or dependencies.
Source: unknown; Homepage: none
If provenance matters for your workspace, verify the publisher before relying on the skill.