Propose a patch

Evidence

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

diff --git a/src/photos_maintenance/definitions/google.toml b/src/photos_maintenance/definitions/google.toml
--- a/src/photos_maintenance/definitions/google.toml
+++ b/src/photos_maintenance/definitions/google.toml
@@ -64,1 +64,0 @@
-…fy')", "button:has-text('Other options')"] password_choice = ["button:has-text('Enter your password')", "div[role='link']:has-text('Enter your password')", "div[role='button']:has…
@@ -117,1 +116,0 @@
-any_text = ["enter your password", "use your password"]
diff --git a/src/photos_mcp/view.html b/src/photos_mcp/view.html
--- a/src/photos_mcp/view.html
+++ b/src/photos_mcp/view.html
@@ -7,1 +7,0 @@
-photos_show (MCP Apps, protocol 2026-01-26): the host loads this page in a sandboxed frame, answers ui/initialize, then sends the tool's input and result. The t

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.14.4. 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: google-photos-mcp: Prompting user to enter sensitive credentials (KillerSkills verdict caution 70)

## 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 70/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/google-photos-mcp/0.14.4

## Findings with a location
- `src/photos_maintenance/definitions/google.toml:117` · Prompting user to enter sensitive credentials — src/photos_maintenance/definitions/google.toml:117 · Prompting user to enter sensitive credentials — social engineering
- `src/photos_maintenance/definitions/google.toml:64` · Prompting user to enter sensitive credentials — src/photos_maintenance/definitions/google.toml:64 · Prompting user to enter sensitive credentials — social engineering
- `src/photos_mcp/view.html:7` · HTML comment carrying imperative instructions to the agent — src/photos_mcp/view.html:7 · HTML comment carrying imperative instructions to the agent · informational: not an instruction file

## 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._