← workplace@1.0.0

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. 52 · Caution

Evidence

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

Diff · removes 4 caught lines

Download .patch
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -129,1 +129,0 @@
-Run `workplace sync claude` to generate/update `CLAUDE.md` at your project root with workplace context — structure, agent roles, conventions, and deploy info.
diff --git a/references/commands.md b/references/commands.md
--- a/references/commands.md
+++ b/references/commands.md
@@ -214,1 +214,0 @@
-> workplace sync claude    # Generate/update CLAUDE.md
diff --git a/references/ide-sync.md b/references/ide-sync.md
--- a/references/ide-sync.md
+++ b/references/ide-sync.md
@@ -89,1 +89,0 @@
-5. Write `CLAUDE.md`
diff --git a/assets/templates/deploy/main.md b/assets/templates/deploy/main.md
--- a/assets/templates/deploy/main.md
+++ b/assets/templates/deploy/main.md
@@ -5,1 +5,0 @@
-List tools, access, credentials needed

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.0. 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: workplace: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 52)

## 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 52/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/workplace/1.0.0

## Findings with a location
- `README.md:129` · Instructs the agent to modify its persistent memory or instruction files — README.md:129 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `references/commands.md:214` · Instructs the agent to modify its persistent memory or instruction files — references/commands.md:214 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `references/ide-sync.md:89` · Instructs the agent to modify its persistent memory or instruction files — references/ide-sync.md:89 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `assets/templates/deploy/main.md:5` · HTML comment carrying imperative instructions to the agent — assets/templates/deploy/main.md:5 · HTML comment carrying imperative instructions to the agent

## 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._
# or from a terminal, under your own account:
gh repo fork openclaw/openclaw --clone && cd openclaw
curl -s https://killerskills.ai/skills/clawhub/workplace/1.0.0/patch.diff | git apply --unidiff-zero
git checkout -b killerskills/1.0.0 && git commit -am "workplace: Instructs the agent to modify its persistent memory or instruction files"
gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/workplace/1.0.0/patch.md)

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.