@softure-ai/skills@0.1.2
SOFTURE agent skills: a spec-driven delivery workflow (shape → prd → roadmap → plan → implement → review) plus parallel worktree orchestration
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe postinstall hook makes first-party skills and agent rules available automatically in consumer projects, creating a real agent-configuration lifecycle risk. Because the changes are package-owned setup with an uninstall path, classify it as suspicious and warn rather than block.
Decision evidence
public snapshot- package.json runs the installer automatically through a postinstall hook.
- The installer targets the consumer project's .claude directory and chooses AGENTS.md or CLAUDE.md for its rules block.
- The installer writes the package's rules into that file without a consent check; the write is skipped only in dry-run mode.
- The uninstall script removes installed skills and strips its managed blocks.
- The setup installs this package's own skills and rules, matching its stated purpose; policy treats this first-party extension setup as warning-level risk.
- The inspected installer and uninstaller show no network transfer or credential collection.
Source & flagged code
8 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgpackage.json runs the installer automatically through a postinstall hook.
package.jsonView on unpkg · L23Findings
Affected versions and remediation
This report applies to @softure-ai/skills@0.1.2.
See all versions of @softure-ai/skills for other recorded verdicts.
- Review the evidence and your use of @softure-ai/skills@0.1.2 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.