Propose a patch

Evidence

The sandbox observed nothing beyond the static findings; the proposal cites those.

diff --git a/dist/notes/home.js b/dist/notes/home.js
--- a/dist/notes/home.js
+++ b/dist/notes/home.js
@@ -146,1 +146,0 @@
-* `[email protected]:NanoNets/Graft.git`, `https://user:[email protected]/NanoNets/Graft`
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -69,1 +69,0 @@
-| You write and update CLAUDE.md by hand | Learnings are saved from your conversations, in files you can read |
@@ -410,1 +409,0 @@
-<summary><b>Method</b></summary> Two clones of PocketBase at the same commit: one wired with `graft init`, one untouched and verified to have no graft map in it
diff --git a/dist/cli-picker.js b/dist/cli-picker.js
--- a/dist/cli-picker.js
+++ b/dist/cli-picker.js
@@ -458,1 +458,0 @@
-// Codex, Hermes and Antigravity all write AGENTS.md: list each write once.

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.29.0. If the behavior is intended, declare it (host under permissions.network, a line in the README) instead of removing it; the next crawl scores declarations.

Issue / PR body

Title: graft: URL with embedded credentials (KillerSkills verdict caution 59)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.7) and scored it **CAUTION 59/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/graft/0.29.0

## Findings with a location
- `dist/notes/home.js:146` · URL with embedded credentials — dist/notes/home.js:146 · URL with embedded credentials — may be phishing or credential leaking
- `README.md:410` · Collapsed <details> block carrying instructions — README.md:410 · Collapsed <details> block carrying instructions
- `README.md:69` · Instructs the agent to modify its persistent memory or instruction files — README.md:69 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `dist/cli-picker.js:458` · Instructs the agent to modify its persistent memory or instruction files — dist/cli-picker.js:458 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 4 lines above. If the behavior is intended, the fix is to declare it instead: list the host under `permissions.network` (or the MCP manifest) and say in the README why the package needs it; the next crawl will re-score it with the declaration taken into account.

## How this will be verified
Nothing is "verified safe" by assertion. When a new version is published, KillerSkills re-runs it in the honeypot and the verdict page updates; you can trigger it early from the verdict page ("Re-scan after I publish a fix"). Reply here or at [email protected] if you believe the verdict is wrong; disputes are reviewed by a person and the outcome is published on the verdict page.

_Proposed through killerskills.ai/threats by a user of the package, under their own GitHub account. The evidence is public; the package was never modified by KillerSkills._