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. 72 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 12 caught lines
Download .patchdiff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -34,1 +34,0 @@
-2. Extract significant items → update MEMORY.md
@@ -94,1 +93,0 @@
-### When to Update MEMORY.md
@@ -116,1 +114,0 @@
-a. Is it already in MEMORY.md? → Skip or update
@@ -118,1 +115,0 @@
-c. Is it important? → Add to MEMORY.md
@@ -120,1 +116,0 @@
-5. Write updated MEMORY.md
diff --git a/scripts/consolidate.py b/scripts/consolidate.py
--- a/scripts/consolidate.py
+++ b/scripts/consolidate.py
@@ -33,1 +33,0 @@
-"label": "PROJECT — update project context in MEMORY.md",
@@ -114,1 +113,0 @@
-print("Review the items above and decide what to add to MEMORY.md.")
diff --git a/references/consolidation.md b/references/consolidation.md
--- a/references/consolidation.md
+++ b/references/consolidation.md
@@ -28,1 +28,0 @@
-6. Write updated MEMORY.md with consolidated content
@@ -38,1 +37,0 @@
-3. If found, update MEMORY.md immediately
@@ -46,1 +44,0 @@
-| "I prefer/like/don't like..." | PERSISTENT | Add to MEMORY.md |
@@ -47,1 +44,0 @@
-| "We decided to..." | PERSISTENT | Add to MEMORY.md |
@@ -51,1 +47,0 @@
-| "I learned that..." | PERSISTENT | Add to MEMORY.md if broadly useful |
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: autobiographical-memory: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 72)
## 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 72/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/autobiographical-memory/1.0.0 ## Findings with a location - `SKILL.md:118` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:118 · Instructs the agent to modify its persistent memory or instruction files - `scripts/consolidate.py:114` · Instructs the agent to modify its persistent memory or instruction files — scripts/consolidate.py:114 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `scripts/consolidate.py:33` · Instructs the agent to modify its persistent memory or instruction files — scripts/consolidate.py:33 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `SKILL.md:116` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:116 · Instructs the agent to modify its persistent memory or instruction files - `references/consolidation.md:28` · Instructs the agent to modify its persistent memory or instruction files — references/consolidation.md:28 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `references/consolidation.md:47` · Instructs the agent to modify its persistent memory or instruction files — references/consolidation.md:47 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `SKILL.md:34` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:34 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:94` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:94 · Instructs the agent to modify its persistent memory or instruction files - `references/consolidation.md:51` · Instructs the agent to modify its persistent memory or instruction files — references/consolidation.md:51 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `SKILL.md:120` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:120 · Instructs the agent to modify its persistent memory or instruction files - `references/consolidation.md:38` · Instructs the agent to modify its persistent memory or instruction files — references/consolidation.md:38 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `references/consolidation.md:46` · Instructs the agent to modify its persistent memory or instruction files — references/consolidation.md:46 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file ## Proposed change The attached patch removes the 12 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._
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.