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. 58 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 4 caught lines
Download .patchdiff --git a/SKILL.md b/SKILL.md --- a/SKILL.md +++ b/SKILL.md @@ -331,1 +331,0 @@ -2. `python3 scripts/run_imagine.py "<prompt>" --transport browser --sync-user-state` @@ -332,1 +331,0 @@ -3. `python3 scripts/run_imagine.py "<prompt>" --transport browser --sync-user-state --wait-page-assets --download` diff --git a/references/operating-model.md b/references/operating-model.md --- a/references/operating-model.md +++ b/references/operating-model.md @@ -10,1 +10,0 @@ -4. Submit one prompt with `python3 scripts/run_imagine.py "<prompt>" --sync-user-state` @@ -12,1 +11,0 @@ -6. Use `python3 scripts/run_imagine.py "<prompt>" --sync-user-state --wait-page-assets --download --convert-to png` when you need a verified local result
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.2. 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: auto-midjourney: Fake instruction boundary tag (KillerSkills verdict caution 58)
## 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 58/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/auto-midjourney/0.1.2 ## Findings with a location - `SKILL.md:332` · Fake instruction boundary tag — SKILL.md:332 · Fake instruction boundary tag - `SKILL.md:331` · Fake instruction boundary tag — SKILL.md:331 · Fake instruction boundary tag - `references/operating-model.md:12` · Fake instruction boundary tag — references/operating-model.md:12 · Fake instruction boundary tag · informational: not an instruction file - `references/operating-model.md:10` · Fake instruction boundary tag — references/operating-model.md:10 · Fake instruction boundary tag · 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._
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.