Propose a patch

Evidence

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

diff --git a/src/browser/aria.ts b/src/browser/aria.ts
--- a/src/browser/aria.ts
+++ b/src/browser/aria.ts
@@ -103,1 +103,0 @@
-.replace(/[‎‏‪-‮⁦-⁩­]/g, '')
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -11,1 +11,0 @@
-A second session navigates to a site and receives what the first session learned, without asking

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.0. 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: browser-memory: Hidden zero-width characters detected (KillerSkills verdict caution 69)

## 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 69/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/browser-memory/1.0.0

## Findings with a location
- `src/browser/aria.ts:103` · Hidden zero-width characters detected — src/browser/aria.ts:103 · Hidden zero-width characters detected — may conceal content
- `README.md:11` · Image alt text carrying instructions — README.md:11 · Image alt text carrying instructions · informational: not an instruction file · informational: not an instruction file

## Proposed change
The attached patch removes the 2 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._