mine-plugins — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited mine-plugins (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This skill requires Python 3.8+ and standard library only. No external packages needed.
To install this skill's dependencies:
pip-compile ./requirements.in
pip install -r ./requirements.txtSee ./requirements.txt for the dependency lockfile (currently empty — standard library only).
Run the full analysis pipeline on a plugin or collection of plugins. This is the one-shot command for the virtuous cycle.
analyze-plugin skillsynthesize-learnings skill/mine-plugins <path-to-plugin-or-directory># Analyze a single plugin
/mine-plugins claude-knowledgework-plugins/sales
# Analyze an entire collection
/mine-plugins claude-knowledgework-plugins/
# Analyze our own plugins
/mine-plugins plugins/legacy\ systemCheck if $ARGUMENTS points to:
.claude-plugin/plugin.json or skills/ directory) → Single Plugin ModeSKILL.md) → Single Skill ModeFor each plugin in scope, run:
python "scripts/inventory_plugin.py" --path "$ARGUMENTS" --format jsonSecurity scanning is enabled by default. The inventory script runs credential detection, network call detection, and environment variable access checks on every script file. Pass --no-security only if you want to suppress the security scan output.If the script fails, perform manual inventory per the analyze-plugin skill Phase 1.
For each plugin, execute the full 6-phase analyze-plugin framework:
If analyzing multiple plugins, identify:
Invoke the synthesize-learnings skill to produce targeted recommendations for:
agent-scaffolders — template and scaffold improvementsagent-scaffolders — standards and spec updatesagent-scaffolders — self-improvement of this analyzeroracle-legacy-system-analysis) — transferable patterns for legacy code analysisPresent the full analysis as a structured markdown artifact. Include:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.