The agentic code harness — open, typed, auditable. Code intelligence, execution sandboxing and 50-dimension quality gates for AI coding agents. One Rust binary, local-first, no telemetry.
- capability exposure inferred + 22
- tool safety inferred + 12
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 2h ago · see ecosystem CVEs →
- C · 43 → B · 31
- C · 51 → C · 43
- C · 43 → C · 51
No known CVEs for this server.
- high dangerous code
committed secret: private key, GitHub token, AWS access key id, OpenAI key, Anthropic key · dynamic exec: eval()
analyzed commit 24e901a · analyzer v33 · 2d ago
skills & prompt files 25
- agent-rules gabrielgadea-touring-24e901a/CLAUDE.md
- skill gabrielgadea-touring-24e901a/Touring.skill!/Touring/SKILL.md
- agent-rules gabrielgadea-touring-24e901a/Touring.skill!/Touring/references/agents.md
- skill gabrielgadea-touring-24e901a/client/skills/TACO-cross-audit/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/TACO-skilling/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/TACO-subagent/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/TACO-wt/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/Touring/SKILL.md
- agent-rules gabrielgadea-touring-24e901a/client/skills/Touring/references/agents.md
- agent-rules gabrielgadea-touring-24e901a/client/skills/loop-engineering/AGENTS.md
- skill gabrielgadea-touring-24e901a/client/skills/loop-engineering/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/taco-planning/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/touring-elite/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/touring-evolve/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/touring-excellence/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/touring-file-metadata/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/touring-generator/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/touring-query/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/touring-scip/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/touring-search/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/touring-token-efficient-workflow/SKILL.md
- skill gabrielgadea-touring-24e901a/client/skills/touring-wiring-suggest/SKILL.md
- agent-rules gabrielgadea-touring-24e901a/crates/touring-analysis/.claude/CLAUDE.md
- agent-rules gabrielgadea-touring-24e901a/crates/touring-generator/.claude/CLAUDE.md
- agent-rules gabrielgadea-touring-24e901a/crates/touring-server/.claude/CLAUDE.md
danger signals8
- dynamic code execution eval() gabrielgadea-touring-24e901a/crates/touring-web/dist/touring-web-d3e1b058fa9ce534.js :371
const ret = eval(getStringFromWasm0(arg0, arg1)); - committed secret GitHub token gabrielgadea-touring-24e901a/crates/touring-ceg/src/gateway/sandbox_executor.rs :1213
ghp_01…(40 chars, redacted) - committed secret AWS access key id gabrielgadea-touring-24e901a/crates/touring-ceg/src/gateway/sandbox_executor.rs :1214
AKIA01…(20 chars, redacted) - committed secret OpenAI key gabrielgadea-touring-24e901a/crates/touring-ceg/src/gateway/sandbox_executor.rs :1214
sk-pro…(28 chars, redacted) - committed secret private key gabrielgadea-touring-24e901a/crates/touring-ceg/src/gateway/sandbox_executor.rs :1240
PEM private key block (redacted) - committed secret GitHub token gabrielgadea-touring-24e901a/crates/touring-quality/src/scope_report.rs :380
ghp_01…(40 chars, redacted) - committed secret GitHub token gabrielgadea-touring-24e901a/crates/touring-quality/src/verifications/f2_4_secrets.rs :915
gho_16…(40 chars, redacted) - committed secret Anthropic key gabrielgadea-touring-24e901a/crates/touring-quality/src/verifications/f2_4_secrets.rs :1173
sk-ant…(35 chars, redacted)
[](https://mcpobservatory.com/servers/github:gabrielgadea/touring/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of gabrielgadea.