Propose a patch

A fix the maintainer can act on, with the evidence attached. It opens under your GitHub account in your browser; KillerSkills holds no token and never modifies the package. The fix is verified the only way we verify anything: the next crawl re-runs the new version in the honeypot. 69 · Caution

Evidence

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

Diff · removes 2 caught lines

Download .patch

diff --git a/references/provider-cli.md b/references/provider-cli.md
--- a/references/provider-cli.md
+++ b/references/provider-cli.md
@@ -130,1 +130,0 @@
-| 501 | 缺必填参数 | `error: required option '--prompt <prompt>' not specified` |
diff --git a/references/model-flags.md b/references/model-flags.md
--- a/references/model-flags.md
+++ b/references/model-flags.md
@@ -13,1 +13,0 @@
---prompt <prompt>            Prompt

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.31. 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: item-repair: Fake instruction boundary tag (KillerSkills verdict caution 69)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.8.1) and scored it **CAUTION 69/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/item-repair/1.0.31

## Findings with a location
- `references/provider-cli.md:130` · Fake instruction boundary tag — references/provider-cli.md:130 · Fake instruction boundary tag · informational: not an instruction file
- `references/model-flags.md:13` · Fake instruction boundary tag — references/model-flags.md:13 · Fake instruction boundary tag · informational: not an instruction file

## Proposed change
The attached patch removes the 2 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._

Open the issue on GitHub (dlazy-ai/ecommerce-skills)Fork to open a PR

# or from a terminal, under your own account:
gh repo fork dlazy-ai/ecommerce-skills --clone && cd ecommerce-skills
curl -s https://killerskills.ai/skills/clawhub/item-repair/1.0.31/patch.diff | git apply --unidiff-zero
git checkout -b killerskills/1.0.31 && git commit -am "item-repair: Fake instruction boundary tag"
gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/item-repair/1.0.31/patch.md)

We count proposals opened, not merged: a merge shows up as a new version that the crawl re-runs. Disputes: the maintainer can contest the verdict from its page; a person reviews it and the outcome is published.