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
@@ -339,1 +339,0 @@
-…finally made it clear and suggests a rule. Nothing is written until you press **Write** on a rule and pick where it goes: **project rules** (the project's CLAUDE.md and AGENTS.md, under "Rules from retros"), **this line** (a decision on the lin…
diff --git a/CHANGELOG.md b/CHANGELOG.md
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -116,1 +116,0 @@
-…e sentence that made it clear and a rule; a rule is written only when you press Write, to the project's CLAUDE.md and AGENTS.md, the line, or long-term memory. - **Fewer tokens:** `trace_tasks` answers for t…
diff --git a/bin/trace-canvas.mjs b/bin/trace-canvas.mjs
--- a/bin/trace-canvas.mjs
+++ b/bin/trace-canvas.mjs
@@ -114,1 +114,0 @@
-Write suggestion n: CLAUDE.md/AGENTS.md, the line, or long-term memory
diff --git a/docs/phone.md b/docs/phone.md
--- a/docs/phone.md
+++ b/docs/phone.md
@@ -40,1 +40,0 @@
-claude --remote-control='<line name>' '<prompt>'

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.3.5. 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: trace-canvas: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 79)

## 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 79/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/trace-canvas/0.3.5

## Findings with a location
- `README.md:339` · Instructs the agent to modify its persistent memory or instruction files — README.md:339 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `CHANGELOG.md:116` · Instructs the agent to modify its persistent memory or instruction files — CHANGELOG.md:116 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `bin/trace-canvas.mjs:114` · Instructs the agent to modify its persistent memory or instruction files — bin/trace-canvas.mjs:114 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `docs/phone.md:40` · Fake instruction boundary tag — docs/phone.md:40 · Fake instruction boundary tag · informational: not an instruction file

## 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._