@cotal-ai/cli@0.133.5
Cotal mesh CLI: up, join, watch, console, spawn, mint, channels, history, ext.
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe flagged agent-skill writes are part of the CLI's setup feature and are limited to its authored skill files. Feedback transmission is performed by the explicit feedback command; no concrete attack behavior was found.
Decision evidence
public snapshot- The package exports CLI modules, including its main entry point and a separate dispatcher.
- Skill reconciliation runs when the user invokes `cotal setup --skills`.
- Reconciliation installs the package's authored `SKILL.md` files under `~/.agents/skills/<name>/` and writes only those files.
- Feedback network requests are made by the explicit feedback command.
Source & flagged code
6 flaggedPackage source references child process execution.
dist/seed/reconcile.jsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @cotal-ai/cli@0.133.5.
See all versions of @cotal-ai/cli for other recorded verdicts.
- Review the evidence and your use of @cotal-ai/cli@0.133.5 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.