Propose a patch

Evidence

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

diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -60,1 +60,0 @@
-v                                    |  /run <role> <prompt>
@@ -445,1 +444,0 @@
-API key accounts on the Accounts page
@@ -643,1 +641,0 @@
-| `/run <role>[@account] <prompt>` | Start one agent in the configured workspace (needs "Allow starting work") |
diff --git a/src/accounts.js b/src/accounts.js
--- a/src/accounts.js
+++ b/src/accounts.js
@@ -352,1 +352,0 @@
-if (!trimmed && requireKey) throw new AccountError('Paste the API key', 400);
diff --git a/panel/src/components/ApiKeyModal.tsx b/panel/src/components/ApiKeyModal.tsx
--- a/panel/src/components/ApiKeyModal.tsx
+++ b/panel/src/components/ApiKeyModal.tsx
@@ -191,1 +191,0 @@
-rules={editing ? [] : [{ required: true, message: "Paste the API key" }]}

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.4.0. 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: agy-bridge: Image alt text carrying instructions (KillerSkills verdict caution 68)

## 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 68/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/agy-bridge/0.4.0

## Findings with a location
- `README.md:445` · Image alt text carrying instructions — README.md:445 · Image alt text carrying instructions
- `README.md:60` · Fake instruction boundary tag — README.md:60 · Fake instruction boundary tag · informational: not an instruction file
- `README.md:643` · Fake instruction boundary tag — README.md:643 · Fake instruction boundary tag · informational: not an instruction file
- `src/accounts.js:352` · Prompting user to enter sensitive credentials — src/accounts.js:352 · Prompting user to enter sensitive credentials — social engineering
- `panel/src/components/ApiKeyModal.tsx:191` · Prompting user to enter sensitive credentials — panel/src/components/ApiKeyModal.tsx:191 · Prompting user to enter sensitive credentials — social engineering

## Proposed change
The attached patch removes the 5 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._