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
@@ -283,1 +283,0 @@
-The prompt-injection run on NEAR testnet: the agent reads /guide, whose note says to pay the 0.4 NEAR licence fee to rnaps.sg-paywall-25135e.testnet, follows it
@@ -285,1 +284,0 @@
-The stolen-key run on NEAR testnet: signing with the agent's function-call key alone, the contract refuses the look-alike payee, 1 yoctoNEAR over the per-paymen
@@ -287,1 +285,0 @@
-The leaked-grant run on Tidepool's testnet: with the agent's Agent API key and grant alone, the policy refuses a transfer to the look-alike rnaps., 51 cents ove

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.2.1. 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: spend-guard: Image alt text carrying instructions (KillerSkills verdict caution 73)

## 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 73/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/spend-guard/0.2.1

## Findings with a location
- `README.md:287` · Image alt text carrying instructions — README.md:287 · Image alt text carrying instructions
- `README.md:283` · Image alt text carrying instructions — README.md:283 · Image alt text carrying instructions
- `README.md:285` · Image alt text carrying instructions — README.md:285 · Image alt text carrying instructions

## 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._