← glm-image@1.9.0

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. 66 · Caution

Evidence

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

Diff · removes 5 caught lines

Download .patch
diff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -101,1 +101,0 @@
-python3 scripts/generate.py "<prompt>" --language <code>
@@ -119,1 +118,0 @@
-python3 scripts/generate.py "<prompt>" --language <zh|en|ja|ko|fr|de|es>
@@ -126,1 +124,0 @@
-python3 scripts/generate.py "<prompt>" --language en --provider openrouter --model google/gemini-2.5-flash-image-preview
@@ -129,1 +126,0 @@
-python3 scripts/generate.py "<prompt>" --language zh --provider glm
@@ -162,1 +158,0 @@
-1. Local file path: `output/<timestamp>_<prompt>.png`

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.9.0. 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: glm-image: Fake instruction boundary tag (KillerSkills verdict caution 66)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.9.2) and scored it **CAUTION 66/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/glm-image/1.9.0

## Findings with a location
- `SKILL.md:126` · Fake instruction boundary tag — SKILL.md:126 · Fake instruction boundary tag
- `SKILL.md:101` · Fake instruction boundary tag — SKILL.md:101 · Fake instruction boundary tag
- `SKILL.md:162` · Fake instruction boundary tag — SKILL.md:162 · Fake instruction boundary tag
- `SKILL.md:119` · Fake instruction boundary tag — SKILL.md:119 · Fake instruction boundary tag
- `SKILL.md:129` · Fake instruction boundary tag — SKILL.md:129 · Fake instruction boundary tag

## Proposed change
The attached patch removes the 5 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._
# or from a terminal, under your own account:
gh repo fork ViffyGwaanl/glm-image --clone && cd glm-image
curl -s https://killerskills.ai/skills/clawhub/glm-image/1.9.0/patch.diff | git apply --unidiff-zero
git checkout -b killerskills/1.9.0 && git commit -am "glm-image: Fake instruction boundary tag"
gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/glm-image/1.9.0/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.