@softure-ai/skills@0.8.0
SOFTURE agent skills: a spec-driven delivery workflow (shape → prd → roadmap → plan → implement → review) plus parallel worktree orchestration
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe install hook automatically changes agent configuration in consumer projects, which leaves a residual lifecycle risk. The changes install package-owned skills and matching workflow rules, and the inspected source does not establish malicious behavior.
Decision evidence
public snapshot- The package runs scripts/install.mjs from its postinstall hook.
- The installer selects the package's skills for installation and skips existing skill folders it does not manage.
- The installer targets the consumer project's AGENTS.md or CLAUDE.md and writes a managed rules block there.
- The injected rules prescribe project workflows and agent operating modes.
- The uninstall script removes installed skills and strips managed blocks.
- The configuration and skills are package-owned and match the package's stated purpose.
- The source shows no unrelated credential transfer or network endpoint in the reviewed installation behavior.
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 unpkgThe package runs scripts/install.mjs from its postinstall hook.
package.jsonView on unpkg · L22Findings
Affected versions and remediation
This report applies to @softure-ai/skills@0.8.0.
See all versions of @softure-ai/skills for other recorded verdicts.
- Review the evidence and your use of @softure-ai/skills@0.8.0 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.