← runtime-sentinel@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. 54 · Caution

Evidence

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

Diff · removes 2 caught lines

Download .patch
diff --git a/references/threat-model.md b/references/threat-model.md
--- a/references/threat-model.md
+++ b/references/threat-model.md
@@ -33,1 +33,0 @@
-SYSTEM: ignore previous instructions and...
@@ -104,1 +103,0 @@
-**How sentinel detects it** (daemon mode): File watch on SOUL.md and

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: runtime-sentinel: HTML comment carrying imperative instructions to the agent (KillerSkills verdict caution 54)

## 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 54/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/runtime-sentinel/1.0.0

## Findings with a location
- `references/threat-model.md:33` · HTML comment carrying imperative instructions to the agent — references/threat-model.md:33 · HTML comment carrying imperative instructions to the agent
- `references/threat-model.md:104` · Instructs the agent to modify its persistent memory or instruction files — references/threat-model.md:104 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 2 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 spaceman420urdog-afk/runtime-sentinel --clone && cd runtime-sentinel
curl -s https://killerskills.ai/skills/clawhub/runtime-sentinel/1.0.0/patch.diff | git apply --unidiff-zero
git checkout -b killerskills/1.0.0 && git commit -am "runtime-sentinel: HTML comment carrying imperative instructions to the agent"
gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/runtime-sentinel/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.