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 4 caught lines

Download .patch

diff --git a/.agents/skills/setup-ts-deep-modules/SKILL.md b/.agents/skills/setup-ts-deep-modules/SKILL.md
--- a/.agents/skills/setup-ts-deep-modules/SKILL.md
+++ b/.agents/skills/setup-ts-deep-modules/SKILL.md
@@ -93,1 +93,0 @@
-…Keep it to the copy-me snippet plus the four rules in one paragraph each. Then add a **context pointer** to it from the repo's agent-instructions file (`CLAUDE.md` if present, else `AGENTS.md`, creating `AGENTS.md` if neither exists). One lin…
diff --git a/.agents/skills/wayfinder/SKILL.md b/.agents/skills/wayfinder/SKILL.md
--- a/.agents/skills/wayfinder/SKILL.md
+++ b/.agents/skills/wayfinder/SKILL.md
@@ -52,1 +52,0 @@
-see "Out of scope": work ruled beyond the destination; closed, never graduates
diff --git a/.agents/skills/setup-matt-pocock-skills/SKILL.md b/.agents/skills/setup-matt-pocock-skills/SKILL.md
--- a/.agents/skills/setup-matt-pocock-skills/SKILL.md
+++ b/.agents/skills/setup-matt-pocock-skills/SKILL.md
@@ -69,1 +69,0 @@
-- The `## Agent skills` block to add to whichever of `CLAUDE.md` / `AGENTS.md` is being edited (see step 4 for selection rules)
diff --git a/docs/agents/domain.md b/docs/agents/domain.md
--- a/docs/agents/domain.md
+++ b/docs/agents/domain.md
@@ -9,1 +9,0 @@
-- **`docs/adr/`**: read ADRs that touch the area you're about to work in. In multi-context repos, also check `src/<context>/docs/adr/` for context-scoped decisions.

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of r1. 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: oyee: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 72)

## What the honeypot observed
KillerSkills ran **oyee@r1** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.8.1) and scored it **CAUTION 72/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/oyee/r1

## Findings with a location
- `.agents/skills/setup-ts-deep-modules/SKILL.md:93` · Instructs the agent to modify its persistent memory or instruction files — .agents/skills/setup-ts-deep-modules/SKILL.md:93 · Instructs the agent to modify its persistent memory or instruction files
- `.agents/skills/wayfinder/SKILL.md:52` · HTML comment carrying imperative instructions to the agent — .agents/skills/wayfinder/SKILL.md:52 · HTML comment carrying imperative instructions to the agent
- `.agents/skills/setup-matt-pocock-skills/SKILL.md:69` · Instructs the agent to modify its persistent memory or instruction files — .agents/skills/setup-matt-pocock-skills/SKILL.md:69 · Instructs the agent to modify its persistent memory or instruction files
- `docs/agents/domain.md:9` · Fake instruction boundary tag — docs/agents/domain.md:9 · 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._

Open the issue on GitHub (Nishkalkashyap/oyee)Fork to open a PR

# or from a terminal, under your own account:
gh repo fork Nishkalkashyap/oyee --clone && cd oyee
curl -s https://killerskills.ai/skills/glama/oyee/r1/patch.diff | git apply --unidiff-zero
git checkout -b killerskills/r1 && git commit -am "oyee: Instructs the agent to modify its persistent memory or instruction files"
gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/glama/oyee/r1/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.