Awardopedia — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Awardopedia (Agent Skill) and scored it 91/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 0 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} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.
ignore/disregard/forget … previous instructions sentence.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.
Free, searchable interface for U.S. federal contract award data sourced from USASpending.gov.
# Clone
git clone https://github.com/openclaw/awardopedia.git
cd awardopedia
# Database
psql -d your_db -f scripts/schema.sql
# API
cd api
cp ../.env.example .env # Edit with your values
npm install
npm run dev # Starts on :3001
# Frontend (separate terminal)
cd web
npm install
npm run dev # Starts on :3000, proxies /api to :3001See .env.example for all required variables. At minimum for local dev:
DATABASE_URL=postgresql://localhost:5432/awardopedia
JWT_SECRET=any-dev-secret
PORT=3001awardopedia/
├── api/ # Express API server
│ ├── src/
│ │ ├── db/ # Database connection + queries
│ │ ├── middleware/ # Auth, credits, rate limiting
│ │ ├── routes/ # API route handlers
│ │ └── services/ # Claude AI, Stripe, SendGrid
│ └── Dockerfile
├── web/ # React + Vite frontend
│ ├── src/
│ │ ├── components/ # Reusable UI components
│ │ ├── pages/ # Route pages
│ │ ├── styles/ # CSS tokens, global, components
│ │ └── utils/ # API client, formatters, SEO
│ └── public/
├── scripts/
│ ├── schema.sql # PostgreSQL schema
│ ├── ingest.py # Bulk CSV ingestion
│ └── sync.py # Weekly USASpending API sync
├── docs/
│ ├── api.md # API endpoint reference
│ ├── data-model.md # Database schema docs
│ └── deployment.md # Deployment guide
└── assets/ # Brand logosAll contract data is sourced from USASpending.gov, the official open data source of federal spending information maintained by the U.S. Department of the Treasury as mandated by FFATA.
python3 scripts/ingest.py --file contracts.csvpython3 scripts/sync.py (fetches last 7 days from USASpending API)Proprietary. Data sourced from USASpending.gov (public domain).
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.