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
@@ -11,1 +11,0 @@
-mcp-warden demo: the agent calls the GitHub API through a preset without seeing the token, a prompt-injected DELETE is refused before any request is sent and la
diff --git a/src/executor/sftp.rs b/src/executor/sftp.rs
--- a/src/executor/sftp.rs
+++ b/src/executor/sftp.rs
@@ -246,1 +246,0 @@
-// `~/.ssh/id_ed25519` is that key under another name, which no path
@@ -682,1 +681,0 @@
-/// A hard link has no path to resolve: /tmp/x linked to ~/.ssh/id_* is
diff --git a/plugins/mcp-warden/skills/using-mcp-warden/SKILL.md b/plugins/mcp-warden/skills/using-mcp-warden/SKILL.md
--- a/plugins/mcp-warden/skills/using-mcp-warden/SKILL.md
+++ b/plugins/mcp-warden/skills/using-mcp-warden/SKILL.md
@@ -125,1 +125,0 @@
-- **Do not** suggest writing credentials to `.env`, `~/.netrc`, `~/.aws/credentials`, etc., as a "workaround" for a missing preset.

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of r1. 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: mcp-warden: Image alt text carrying instructions (KillerSkills verdict caution 62)

## What the honeypot observed
KillerSkills ran **mcp-warden@r1** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.8.1) and scored it **CAUTION 62/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/mcp-warden/r1

## Findings with a location
- `README.md:11` · Image alt text carrying instructions — README.md:11 · Image alt text carrying instructions
- `src/executor/sftp.rs:682` · References a credential file in the home directory — src/executor/sftp.rs:682 · References a credential file in the home directory
- `plugins/mcp-warden/skills/using-mcp-warden/SKILL.md:125` · References a credential file in the home directory — plugins/mcp-warden/skills/using-mcp-warden/SKILL.md:125 · References a credential file in the home directory
- `src/executor/sftp.rs:246` · References a credential file in the home directory — src/executor/sftp.rs:246 · References a credential file in the home directory

## 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._