v1.0.0

Ruthless Mentor

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 7:37 AM.

Analysis

This is a benign instruction-only advisory skill, but it delegates your plans to a spawned model session and mentions an optional recurring task review.

GuidanceThis skill is safe to install as an instruction-only advisor if you want critical feedback. Before using it, remember that whatever idea, strategy, or task-file content you provide may be sent to the spawned model session, and do not enable the optional weekly cron unless you want ongoing automated reviews.

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Rogue Agents

SeverityLowConfidenceHighStatusNote

SKILL.md

Weekly cron optional: review active-tasks.md and challenge priorities

The artifact suggests an optional recurring schedule that would periodically run the mentor against a task file. No cron job is installed by the artifacts, but enabling it would create ongoing autonomous review.

User impactIf configured, the mentor could run periodically and review the named task file without a fresh manual prompt each time.

RecommendationOnly enable a recurring cron if you explicitly want it, keep the reviewed file scoped, and make the schedule easy to disable.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityLowConfidenceHighStatusNote

SKILL.md

sessions_spawn(
  task: "[paste the idea/plan/workflow to evaluate]\n\n" + [system prompt above],
  model: "anthropic/claude-sonnet-4-20250514"

The intended workflow sends the user's idea, plan, or workflow to a spawned sub-agent/model. This is coherent with the mentor purpose, but it creates a data-sharing boundary the user should notice.

User impactSensitive business plans, strategy notes, or workflow details included in the task could be shared with the spawned model session.

RecommendationAvoid including secrets or confidential material unless you are comfortable sending it to the configured model session.