1 check that ran failed — version behavior — so this release can’t be trusted as-is.
- Publisher
- io.github.eat-pray-ai
- Repository
- github.com/eat-pray-ai/yutu
- Install
- npm:@eat-pray-ai/yutu, npm:@eat-pray-ai/yutu, npm:@eat-pray-ai/yutu, npm:@eat-pray-ai/yutu, oci:ghcr.io/eat-pray-ai/yutu:v0.10.4-dev, oci:ghcr.io/eat-pray-ai/yutu:v0.10.4-dev1, oci:ghcr.io/eat-pray-ai/yutu:v0.10.4-dev2, oci:ghcr.io/eat-pray-ai/yutu:v0.10.5, oci:ghcr.io/eat-pray-ai/yutu:v0.10.5-dev, oci:ghcr.io/eat-pray-ai/yutu:v0.10.6, oci:ghcr.io/eat-pray-ai/yutu:v0.10.6-dev, oci:ghcr.io/eat-pray-ai/yutu:v0.10.7, oci:ghcr.io/eat-pray-ai/yutu:v0.10.7-dev, oci:ghcr.io/eat-pray-ai/yutu:v0.10.7-dev1, oci:ghcr.io/eat-pray-ai/yutu:v0.10.8-dev1, npm:@eat-pray-ai/yutu, npm:@eat-pray-ai/yutu, npm:@eat-pray-ai/yutu, npm:@eat-pray-ai/yutu
- Versions
- 19
- Inspected
- 4 of 6 checks · 65%
- Scored
- 2026-09-02 · rubric 1.0.0
What we checked
Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.
Injection surface
unscannable25% of gradeTool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).
No tool descriptions, server instructions, prompts, or resources were fetched; nothing to scan for injection.
Supply chain
warn25% of gradePackage provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.
package name "@eat-pray-ai/yutu" is edit-distance 2 from popular package "yup" (typosquat candidate)
Credential hygiene
pass15% of gradeHow the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.
No hardcoded secrets, secret-shaped tool parameters, or leaked keys found. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.
Permission scope
pass15% of gradeDeclared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.
No shell-exec, unbounded/sensitive filesystem, or download-and-run primitives found in scanned source. PASS = no static red flag. Static scanning is blind to code fetched or executed at runtime.
Version behavior
fail10% of gradeDiff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).
vs prior 0.10.11-dev2 (other bump): new hardcoded outbound host/BCC destination(s): github.com.
Transport config
unscannable10% of gradeRemote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.
local stdio server: no remote transport or auth surface, and no phone-home/telemetry signal found in source. Absence of transport findings is NOT a safety guarantee — phone-home hosts can be constructed at runtime and defeat static analysis.
Version history
Each release plotted by grade against the safe line at B. A version that sinks below the line has lost its trusted standing — the shape of a rug-pull.
| Version | Published | Grade | Score | Inspected | Change |
|---|---|---|---|---|---|
| v0.10.11-dev3 · current | 2026-08-20 | B | 77.5 | 4/6 · 65% | ±0 |
| v0.10.11-dev2 | 2026-08-01 | B | 87.5 | 4/6 · 65% | ±0 |
| v0.10.11-dev1 | 2026-07-26 | B | 87.5 | 3/6 · 55% | ±0 |
| v0.10.10-dev1 | 2026-06-27 | B | 87.5 | 4/6 · 65% | ±0 |
| v0.10.9 | 2026-06-21 | B | 87.5 | 3/6 · 55% | — |