Blindoracle Docs — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Blindoracle Docs (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 3 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.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.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.
This repo is consolidating into [github.com/craigmbrown/blindoracle-mcp](https://github.com/craigmbrown/blindoracle-mcp) (canonical).
BlindOracle is the trust and counterparty-risk layer for agent-to-agent trades: 39 live pay-per-call services (trust badges, reputation lookups, pre-hire checks, security audits, dispute settlement, research and data), settled in USDC on Base over x402. Every paid call returns a settlement proof anyone can verify.
{ "mcpServers": { "blindoracle": { "url": "https://api.craigmbrown.com/v1/mcp" } } }GET https://api.craigmbrown.com/v1/servicesagent_trust-badge and reputation_lookup are free over MCP for 5 calls a day.Retired: Fedimint/Lightning payments, prediction markets (/v2/forecasts, /v2/hello-world), and the "first 1,000 settlements free" trial. Older posts in blog/ are kept for history only.
Apache-2.0.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.