Edvisage Agent Ops

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This is a coherent instruction-only monitoring skill, but users should know it asks the agent to keep persistent activity/cost logs and the free version does not actually enforce spend limits.

This skill appears safe to install as an instruction-only logging/reporting aid. Before using it, decide whether you are comfortable with your agent keeping persistent logs of actions, targets, and cost estimates, and do not rely on the free version to enforce actual spending limits.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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.

What this means

Your agent may keep a continuing record of what it did, including file/API/tool targets and cost estimates.

Why it was flagged

The skill asks the agent to persist operational logs in memory files, including action targets and outcomes. This is consistent with monitoring, but those logs may contain sensitive workflow metadata and could be reused in later contexts.

Skill content
Maintain a running daily cost log in your memory files ... Every significant action gets logged with ... Action type ... Target ... Outcome
Recommendation

Use this only where persistent operational logs are acceptable; avoid including sensitive content in log entries, review reports before sharing them, and periodically clear old memory logs if needed.

What this means

You might think this skill will stop overspending, but the included free version mainly tracks and flags costs rather than enforcing hard limits.

Why it was flagged

The registry description advertises spending-limit enforcement, while the skill text clarifies that the free version does not enforce spending limits. This is not malicious, but users should not over-trust it as an automatic cost-control guardrail.

Skill content
Description: ... enforce spending limits, detect anomalies ... / Limitations (Free Version): ... No spending limit enforcement
Recommendation

Treat it as a logging and alerting aid unless you independently verify an enforcement feature; set spending caps in your provider/account controls where possible.