1 check that ran failed — credential hygiene — so this release can’t be trusted as-is.
- Publisher
- so.hilt
- Repository
- —
- Install
- remote only
- Versions
- 2
- MCP revision
- 2025-11-25 · superseded
- Inspected
- 5 of 6 checks · 85%
- Scored
- 2026-09-03 · 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
pass25% of gradeTool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).
Scanned 44 text field(s); no instruction-injection patterns found. PASS = no static red flag. A server can serve different tool descriptions at runtime (the rug-pull class), which static scanning cannot see.
Supply chain
warn25% of gradePackage provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.
no resolvable repository linked to the package (provenance unverifiable)
Credential hygiene
fail15% of gradeHow the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.
tool "hilt_claim_api_key" has a secret-shaped input parameter "setup_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "hilt_activate_starter" has a secret-shaped input parameter "setup_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "hilt_activate_growth" has a secret-shaped input parameter "setup_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "hilt_activate_scale" has a secret-shaped input parameter "setup_token" — secrets must never be tool parameters (the model would supply/handle the credential).
Permission scope
unscannable15% of gradeDeclared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.
No source files, package.json, or pyproject were fetched; cannot infer capability scope.
Version behavior
warn10% of gradeDiff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).
vs prior 1.0.0 (minor bump): new tool "hilt_get_offer" appeared; new tool "hilt_get_catalog" appeared; new tool "hilt_get_pricing" appeared; new tool "hilt_create_quote" appeared; new tool "hilt_agent_bootstrap" touches a sensitive surface (email/exec/net/fs); new tool "hilt_claim_api_key" touches a sensitive surface (email/exec/net/fs); new tool "hilt_activate_starter" appeared; new tool "hilt_activate_growth" appeared; new tool "hilt_activate_scale" appeared.
Transport config
pass10% of gradeRemote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.
remote endpoint "https://api.hilt.so/mcp" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)
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 |
|---|---|---|---|---|---|
| v1.1.0 · current | 2026-07-22 | C | 67.5 | 5/6 · 85% | insf→C in v1.1.0 |
| v1.0.0 | 2026-07-15 | insufficient | — | 1/6 · 25% | — |