@softure-ai/skills@0.3.0
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 install hook makes first-party agent skills and managed rules available automatically in the consuming project, a guarded agent extension lifecycle risk. Source inspection found no evidence of a malicious payload, unrelated agent control-surface mutation, or exfiltration.
Decision evidence
public snapshot- package.json runs the installer as a postinstall hook.
- The installer resolves the consumer project from npm's install directory unless a target is supplied.
- The installer copies bundled skills into the consumer's Claude skills directory and writes bundled rules into AGENTS.md or CLAUDE.md without a consent prompt.
- Uninstall removes the manifest-listed skills and strips managed blocks.
- The setup installs this package's own bundled skills and rules, and its writes are marked as managed.
- The installer skips an existing skill folder it does not already manage.
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 as a postinstall hook.
package.jsonView on unpkg · L23Findings
Affected versions and remediation
This report applies to @softure-ai/skills@0.3.0.
See all versions of @softure-ai/skills for other recorded verdicts.
- Review the evidence and your use of @softure-ai/skills@0.3.0 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.