Propose a patch

Evidence

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

diff --git a/docs/deployment/oidc.md b/docs/deployment/oidc.md
--- a/docs/deployment/oidc.md
+++ b/docs/deployment/oidc.md
@@ -206,1 +206,0 @@
-Project-specific notes for OIDC deployment go here; kept across copier update. (E.g. "Keycloak requires X claim", "Authelia token-cache quirk for /admin paths",
diff --git a/src/logodev_mcp/static/app.html b/src/logodev_mcp/static/app.html
--- a/src/logodev_mcp/static/app.html
+++ b/src/logodev_mcp/static/app.html
@@ -2,1 +2,0 @@
-Logo.dev MCP SPA shell placeholder. Run scripts/vendor_spa.py to hydrate this file with the vendored SDK once you're ready to ship MCP Apps UI.
diff --git a/docs/guides/authentication.md b/docs/guides/authentication.md
--- a/docs/guides/authentication.md
+++ b/docs/guides/authentication.md
@@ -233,1 +233,0 @@
-Project-specific notes for authentication go here; kept across copier update. (E.g. "paperless-mcp tokens expire every 60 min", "this server requires the 'admin

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.1.0. 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: logodev-mcp: HTML comment carrying imperative instructions to the agent (KillerSkills verdict caution 64)

## 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 64/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/logodev-mcp/1.1.0

## Findings with a location
- `docs/deployment/oidc.md:206` · HTML comment carrying imperative instructions to the agent — docs/deployment/oidc.md:206 · HTML comment carrying imperative instructions to the agent
- `src/logodev_mcp/static/app.html:2` · HTML comment carrying imperative instructions to the agent — src/logodev_mcp/static/app.html:2 · HTML comment carrying imperative instructions to the agent · informational: not an instruction file
- `docs/guides/authentication.md:233` · HTML comment carrying imperative instructions to the agent — docs/guides/authentication.md:233 · HTML comment carrying imperative instructions to the agent

## Proposed change
The attached patch removes the 3 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._