Propose a patch

Evidence

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

diff --git a/dist/mcp.js b/dist/mcp.js
--- a/dist/mcp.js
+++ b/dist/mcp.js
@@ -5869,1 +5869,0 @@
-…shold, fix the cheapest gap first: install the pre-commit hook for hooks, create AGENTS.md for docs, add .oc-pilot.json for config, run the suite for tests, and run oc-pilot receipt fo…
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -517,1 +517,0 @@
-A suppression without a reason is ignored. `--ignore <rules>` skips whole rules and `--no-suppressions` disables inline suppressions.
@@ -544,1 +543,0 @@
-A suppression without a reason is ignored. `--ignore <rules>` skips whole rules, `--no-suppressions` disables inline suppressions for an audit run.

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.143.0. 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: oc-pilot: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 75)

## 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 75/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/oc-pilot/0.143.0

## Findings with a location
- `dist/mcp.js:5869` · Instructs the agent to modify its persistent memory or instruction files — dist/mcp.js:5869 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `README.md:517` · Fake instruction boundary tag — README.md:517 · Fake instruction boundary tag · informational: not an instruction file
- `README.md:544` · Fake instruction boundary tag — README.md:544 · Fake instruction boundary tag · informational: not an instruction file

## 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._