co-scientist-install — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited co-scientist-install (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 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.
Goal:
Expected input:
Execution steps:
uv quick install:
uv sync --extra dev --extra mcp
pnpm --dir apps/dashboard install
pnpm --dir apps/dashboard build
powershell -File tools/install/install_co_scientist.ps1conda / pip path:
conda create -n co-scientist python=3.12 -y
conda activate co-scientist
python -m pip install -e ".[dev,mcp]"
pnpm --dir apps/dashboard install
pnpm --dir apps/dashboard build
powershell -File tools/install/install_co_scientist.ps1 bash tools/install/install_co_scientist.sh powershell -File tools/install/install_co_scientist.ps1 -Reconcile powershell -File tools/install/install_co_scientist.ps1 -Uninstall uv run python -m tools.host.project_cli doctor.claude/skills/, .co-scientist/installed-skills.json)doctorRules:
skills/ as canonical and .claude/skills/ as the project-local Claude Code mirror.CLAUDE.md; the installer manages its own project-local surface.doctor after installation instead of assuming the environment is ready.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.