blueprint-derive-tests

Warn

Audited by Socket on Mar 1, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

This skill's declared purpose (mining git history for fix/feat commits and producing a Test Regression Plan) is consistent with the operations it performs: running local git commands, scanning the repository for test files, generating a markdown TRP, and updating a local manifest. There are no network downloads, credential harvesting, obfuscated payloads, or known exfiltration endpoints. The primary security considerations are operational: (1) the skill writes and mutates repository files (docs/trps/* and docs/blueprint/manifest.json) which is expected but requires user/agent trust and care to avoid manifest corruption, and (2) it may invoke a Task (/blueprint:init) that introduces transitive actions outside the scope of this file. Overall this appears functionally coherent and not malicious, but you should run it only in a trusted environment and ensure the Task it might call is also reviewed.

Confidence: 85%Severity: 75%
Audit Metadata
Analyzed At
Mar 1, 2026, 06:50 PM
Package URL
pkg:socket/skills-sh/laurigates%2Fclaude-plugins%2Fblueprint-derive-tests%2F@fdab37f62169453c7aecf8b30dad9630879612d7