← discord-soul@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. 61 · Caution

Evidence

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

Diff · removes 4 caught lines

Download .patch
diff --git a/references/security.md b/references/security.md
--- a/references/security.md
+++ b/references/security.md
@@ -14,1 +14,0 @@
-- System prompt injection (`<system>`, `[INST]`, `<<SYS>>`)
@@ -45,1 +44,0 @@
-- `<system>`, `[INST]`, `<<SYS>>`
diff --git a/scripts/simulate_growth.py b/scripts/simulate_growth.py
--- a/scripts/simulate_growth.py
+++ b/scripts/simulate_growth.py
@@ -147,1 +147,0 @@
-3. Update the agent files (SOUL.md, MEMORY.md, etc.) as the prompt instructs
diff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -70,1 +70,0 @@
-- **System injection:** `<system>`, `[INST]`, `<<SYS>>`

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: discord-soul: Fake instruction boundary tag (KillerSkills verdict caution 61)

## 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 61/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/discord-soul/1.0.0

## Findings with a location
- `references/security.md:14` · Fake instruction boundary tag — references/security.md:14 · Fake instruction boundary tag · informational: not an instruction file
- `scripts/simulate_growth.py:147` · Instructs the agent to modify its persistent memory or instruction files — scripts/simulate_growth.py:147 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `references/security.md:45` · Fake instruction boundary tag — references/security.md:45 · Fake instruction boundary tag · informational: not an instruction file
- `SKILL.md:70` · Fake instruction boundary tag — SKILL.md:70 · Fake instruction boundary tag

## 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 Tyrrrz/DiscordChatExporter --clone && cd DiscordChatExporter
curl -s https://killerskills.ai/skills/clawhub/discord-soul/1.0.0/patch.diff | git apply --unidiff-zero
git checkout -b killerskills/1.0.0 && git commit -am "discord-soul: Fake instruction boundary tag"
gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/discord-soul/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.