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. 57 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 6 caught lines
Download .patchdiff --git a/SKILL.md b/SKILL.md --- a/SKILL.md +++ b/SKILL.md @@ -72,1 +72,0 @@ -- **Preferences expressed** — "I like dark mode" → log it AND update MEMORY.md @@ -76,1 +75,0 @@ -- **User corrections** — "Actually, my name is spelled Kody with a K" → log AND update USER.md/MEMORY.md @@ -81,1 +79,0 @@ -2. If it's a long-term fact/preference, ALSO update `MEMORY.md` @@ -124,1 +121,0 @@ -3. **Promote to MEMORY.md** — add distilled, curated entries (not copy-paste from daily notes) @@ -331,1 +327,0 @@ -- Update MEMORY.md to resolve the conflict diff --git a/SETUP-PROMPT.md b/SETUP-PROMPT.md --- a/SETUP-PROMPT.md +++ b/SETUP-PROMPT.md @@ -242,1 +242,0 @@ -2. If it's a lasting preference/fact, also update `MEMORY.md`
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.3. 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: normieclaw-supercharged-memory: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 57)
## 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 57/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/normieclaw-supercharged-memory/1.0.3 ## Findings with a location - `SKILL.md:76` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:76 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:72` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:72 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:124` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:124 · Instructs the agent to modify its persistent memory or instruction files - `SETUP-PROMPT.md:242` · Instructs the agent to modify its persistent memory or instruction files — SETUP-PROMPT.md:242 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `SKILL.md:331` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:331 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:81` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:81 · Instructs the agent to modify its persistent memory or instruction files ## Proposed change The attached patch removes the 6 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.