Propose a patch

Evidence

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

diff --git a/docs/upstream/pages/oauth2.md b/docs/upstream/pages/oauth2.md
--- a/docs/upstream/pages/oauth2.md
+++ b/docs/upstream/pages/oauth2.md
@@ -156,1 +156,0 @@
-Your application sends a token request to the Google Authorization Server, receives an authorization code, exchanges the code for a token, and uses the token to
@@ -184,1 +183,0 @@
-Your application sends a token request to the Google Authorization Server, receives an authorization code, exchanges the code for a token, and uses the token to
@@ -202,1 +200,0 @@
-Your JS application sends a token request to the Google Authorization Server, receives a token, validates the token, and uses the token to call a Google API end
@@ -260,1 +257,0 @@
-Your server application uses a JWT to request a token from the Google Authorization Server, then uses the token to call a Google API endpoint. No end-user is in

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.0. 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: google-mail: Image alt text carrying instructions (KillerSkills verdict caution 79)

## 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 79/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/google-mail/0.1.0

## Findings with a location
- `docs/upstream/pages/oauth2.md:156` · Image alt text carrying instructions — docs/upstream/pages/oauth2.md:156 · Image alt text carrying instructions
- `docs/upstream/pages/oauth2.md:202` · Image alt text carrying instructions — docs/upstream/pages/oauth2.md:202 · Image alt text carrying instructions
- `docs/upstream/pages/oauth2.md:260` · Image alt text carrying instructions — docs/upstream/pages/oauth2.md:260 · Image alt text carrying instructions
- `docs/upstream/pages/oauth2.md:184` · Image alt text carrying instructions — docs/upstream/pages/oauth2.md:184 · Image alt text carrying instructions

## 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._