← proxy-token-optimizer@1.0.1

Propose a patch

A fix the maintainer can act on, with the evidence attached. It opens under your GitHub account in your browser; KillerSkills holds no token and never modifies the package. The fix is verified the only way we verify anything: the next crawl re-runs the new version in the honeypot. 66 · Caution

Evidence

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

Diff · removes 6 caught lines

Download .patch
diff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -16,1 +16,0 @@
-# Proxy Token Optimizer
@@ -66,1 +65,0 @@
-python3 scripts/model_router.py "<prompt>" [provider]
@@ -84,1 +82,0 @@
-python3 scripts/context_optimizer.py recommend "<prompt>"
@@ -133,1 +130,0 @@
-python3 scripts/cli.py route "<prompt>"       # model routing
@@ -134,1 +130,0 @@
-python3 scripts/cli.py context "<prompt>"     # context recommendation
diff --git a/scripts/context_optimizer.py b/scripts/context_optimizer.py
--- a/scripts/context_optimizer.py
+++ b/scripts/context_optimizer.py
@@ -112,1 +112,0 @@
-recommended.add("MEMORY.md")

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.1. 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: proxy-token-optimizer: Fake instruction boundary tag (KillerSkills verdict caution 66)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.9.2) and scored it **CAUTION 66/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/proxy-token-optimizer/1.0.1

## Findings with a location
- `SKILL.md:133` · Fake instruction boundary tag — SKILL.md:133 · Fake instruction boundary tag
- `SKILL.md:84` · Fake instruction boundary tag — SKILL.md:84 · Fake instruction boundary tag
- `scripts/context_optimizer.py:112` · Instructs the agent to modify its persistent memory or instruction files — scripts/context_optimizer.py:112 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `SKILL.md:66` · Fake instruction boundary tag — SKILL.md:66 · Fake instruction boundary tag
- `SKILL.md:134` · Fake instruction boundary tag — SKILL.md:134 · Fake instruction boundary tag
- `SKILL.md:16` · Credential pass-through configuration — SKILL.md:16 · Credential pass-through configuration — agent relays sensitive credentials

## Proposed change
The attached patch removes the 6 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._
No GitHub source is recorded for this package, so there is nothing to open; paste the body into the registry's support channel.

We count proposals opened, not merged: a merge shows up as a new version that the crawl re-runs. Disputes: the maintainer can contest the verdict from its page; a person reviews it and the outcome is published.