← midjourney-proxy-mcp@0.2.1
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. 57 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 9 caught lines
Download .patchdiff --git a/.claude/commands/gh/post-merge.md b/.claude/commands/gh/post-merge.md --- a/.claude/commands/gh/post-merge.md +++ b/.claude/commands/gh/post-merge.md @@ -2,1 +2,0 @@ -description: Clean up branch and update CLAUDE.md after PR merge @@ -93,1 +92,0 @@ -- Example: `git add CLAUDE.md AGENTS.md GEMINI.md 2>/dev/null || true` diff --git a/.claude/commands/tm/convert-prd.md b/.claude/commands/tm/convert-prd.md --- a/.claude/commands/tm/convert-prd.md +++ b/.claude/commands/tm/convert-prd.md @@ -41,1 +41,0 @@ -<context> @@ -45,1 +44,0 @@ -</context> @@ -100,1 +98,0 @@ -<context> @@ -109,1 +106,0 @@ -</context> diff --git a/.claude/commands/tm/post-merge.md b/.claude/commands/tm/post-merge.md --- a/.claude/commands/tm/post-merge.md +++ b/.claude/commands/tm/post-merge.md @@ -7,1 +7,0 @@ -After PR merge, perform branch cleanup, TaskMaster status update, and CLAUDE.md update. @@ -151,1 +150,0 @@ -git add CLAUDE.md AGENTS.md GEMINI.md 2>/dev/null || true diff --git a/src/midjourney_proxy_mcp/client.py b/src/midjourney_proxy_mcp/client.py --- a/src/midjourney_proxy_mcp/client.py +++ b/src/midjourney_proxy_mcp/client.py @@ -54,1 +54,0 @@ -"Set IMAGINEAPI_TOKEN environment variable or pass token parameter."
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.2.1. 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: midjourney-proxy-mcp: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 57)
## 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 57/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/pypi/midjourney-proxy-mcp/0.2.1 ## Findings with a location - `.claude/commands/gh/post-merge.md:93` · Instructs the agent to modify its persistent memory or instruction files — .claude/commands/gh/post-merge.md:93 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `.claude/commands/tm/convert-prd.md:109` · Fake instruction boundary tag — .claude/commands/tm/convert-prd.md:109 · Fake instruction boundary tag · informational: not an instruction file - `.claude/commands/tm/convert-prd.md:41` · Fake instruction boundary tag — .claude/commands/tm/convert-prd.md:41 · Fake instruction boundary tag · informational: not an instruction file - `.claude/commands/tm/post-merge.md:151` · Instructs the agent to modify its persistent memory or instruction files — .claude/commands/tm/post-merge.md:151 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `.claude/commands/tm/convert-prd.md:45` · Fake instruction boundary tag — .claude/commands/tm/convert-prd.md:45 · Fake instruction boundary tag · informational: not an instruction file - `src/midjourney_proxy_mcp/client.py:54` · Credential pass-through configuration — src/midjourney_proxy_mcp/client.py:54 · Credential pass-through configuration — agent relays sensitive credentials - `.claude/commands/gh/post-merge.md:2` · Instructs the agent to modify its persistent memory or instruction files — .claude/commands/gh/post-merge.md:2 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `.claude/commands/tm/convert-prd.md:100` · Fake instruction boundary tag — .claude/commands/tm/convert-prd.md:100 · Fake instruction boundary tag · informational: not an instruction file - `.claude/commands/tm/post-merge.md:7` · Instructs the agent to modify its persistent memory or instruction files — .claude/commands/tm/post-merge.md:7 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file ## Proposed change The attached patch removes the 9 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 YoungjaeDev/midjourney-proxy-mcp --clone && cd midjourney-proxy-mcp curl -s https://killerskills.ai/skills/pypi/midjourney-proxy-mcp/0.2.1/patch.diff | git apply --unidiff-zero git checkout -b killerskills/0.2.1 && git commit -am "midjourney-proxy-mcp: Instructs the agent to modify its persistent memory or instruction files" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/pypi/midjourney-proxy-mcp/0.2.1/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.