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. 55 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 5 caught lines
Download .patchdiff --git a/dependencies/agent-docs/references/advanced-patterns.md b/dependencies/agent-docs/references/advanced-patterns.md --- a/dependencies/agent-docs/references/advanced-patterns.md +++ b/dependencies/agent-docs/references/advanced-patterns.md @@ -243,1 +243,0 @@ -- name: Update AGENTS.md @@ -247,1 +246,0 @@ -(git add AGENTS.md && git commit -m "chore: update AGENTS.md") diff --git a/examples/trading-agent.md b/examples/trading-agent.md --- a/examples/trading-agent.md +++ b/examples/trading-agent.md @@ -25,1 +25,0 @@ -Edit `AGENTS.md`: diff --git a/examples/content-creator-agent.md b/examples/content-creator-agent.md --- a/examples/content-creator-agent.md +++ b/examples/content-creator-agent.md @@ -25,1 +25,0 @@ -Edit `AGENTS.md`: diff --git a/examples/customer-service-agent.md b/examples/customer-service-agent.md --- a/examples/customer-service-agent.md +++ b/examples/customer-service-agent.md @@ -33,1 +33,0 @@ -Edit `AGENTS.md` to add safety rules:
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: agent-dev-toolkit: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 55)
## 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 55/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/agent-dev-toolkit/1.0.0 ## Findings with a location - `dependencies/agent-docs/references/advanced-patterns.md:247` · Instructs the agent to modify its persistent memory or instruction files — dependencies/agent-docs/references/advanced-patterns.md:247 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `dependencies/agent-docs/references/advanced-patterns.md:243` · Instructs the agent to modify its persistent memory or instruction files — dependencies/agent-docs/references/advanced-patterns.md:243 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `examples/trading-agent.md:25` · Instructs the agent to modify its persistent memory or instruction files — examples/trading-agent.md:25 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `examples/content-creator-agent.md:25` · Instructs the agent to modify its persistent memory or instruction files — examples/content-creator-agent.md:25 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `examples/customer-service-agent.md:33` · Instructs the agent to modify its persistent memory or instruction files — examples/customer-service-agent.md:33 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file ## Proposed change The attached patch removes the 5 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 openclaw/agent-dev-toolkit --clone && cd agent-dev-toolkit curl -s https://killerskills.ai/skills/clawhub/agent-dev-toolkit/1.0.0/patch.diff | git apply --unidiff-zero git checkout -b killerskills/1.0.0 && git commit -am "agent-dev-toolkit: Instructs the agent to modify its persistent memory or instruction files" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/agent-dev-toolkit/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.