Propose a patch

Evidence

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

diff --git a/flashcards.md b/flashcards.md
--- a/flashcards.md
+++ b/flashcards.md
@@ -81,1 +81,0 @@
-…k against past-paper frequency first. Run a leech sweep monthly (`## Due`) and write each verdict to `### Leech Log`, under `## Decks` in `memory.md`: date, deck, card, why it failed, what replaced it. Without the log the same c…
diff --git a/notes.md b/notes.md
--- a/notes.md
+++ b/notes.md
@@ -97,1 +97,0 @@
-…write it to `artifacts/<kebab-name>.md` with a line saying when to read it, and add its `## Boxes` line in `memory.md` in the same turn. Every gap the from-memory build exposed goes to `errors.md`,…
diff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -38,1 +38,0 @@
-…chain:university-portal`, `env:ANKI_SYNC_KEY`, `1password:School/Portal`, `file:~/.ssh/id_ed25519`. If data sits at an old location (`~/study/`, `~/clawic/study/`, or the…

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: study: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 65)

## 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 65/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/study/1.0.3

## Findings with a location
- `flashcards.md:81` · Instructs the agent to modify its persistent memory or instruction files — flashcards.md:81 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `notes.md:97` · Instructs the agent to modify its persistent memory or instruction files — notes.md:97 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `SKILL.md:38` · References a credential file in the home directory — SKILL.md:38 · References a credential file in the home directory

## Proposed change
The attached patch removes the 3 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._