← claude-mem@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. 45 · Blocked

Evidence

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

Diff · removes 4 caught lines

Download .patch
diff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -172,1 +172,0 @@
-2. **`tool_result_persist`** — Records each tool use (Read, Write, Bash, etc.) as an observation, re-syncs MEMORY.md
@@ -396,1 +395,0 @@
-Updates are fire-and-forget (non-blocking). The agent is never held up waiting for MEMORY.md to write.
@@ -454,1 +452,0 @@
-| `syncMemoryFile` | boolean | `true` | Write MEMORY.md to agent workspaces |
diff --git a/src/index.ts b/src/index.ts
--- a/src/index.ts
+++ b/src/index.ts
@@ -564,1 +564,0 @@
-api.logger.warn(`[claude-mem] Failed to write MEMORY.md: ${msg}`);

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: claude-mem: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict blocked 45)

## 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 **BLOCKED 45/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/claude-mem/1.0.1

## Findings with a location
- `SKILL.md:454` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:454 · Instructs the agent to modify its persistent memory or instruction files
- `SKILL.md:172` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:172 · Instructs the agent to modify its persistent memory or instruction files
- `SKILL.md:396` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:396 · Instructs the agent to modify its persistent memory or instruction files
- `src/index.ts:564` · Instructs the agent to modify its persistent memory or instruction files — src/index.ts:564 · Instructs the agent to modify its persistent memory or instruction files · 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._
# or from a terminal, under your own account:
gh repo fork thedotmack/claude-mem --clone && cd claude-mem
curl -s https://killerskills.ai/skills/clawhub/claude-mem/1.0.1/patch.diff | git apply --unidiff-zero
git checkout -b killerskills/1.0.1 && git commit -am "claude-mem: Instructs the agent to modify its persistent memory or instruction files"
gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/claude-mem/1.0.1/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.