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. 60 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 5 caught lines
Download .patchdiff --git a/SKILL.md b/SKILL.md --- a/SKILL.md +++ b/SKILL.md @@ -14,1 +14,0 @@ -description: "Direct proxy token for a single credential (starts with pxr_). Simpler but limited to one credential." @@ -35,1 +34,0 @@ -### Option B — Direct Proxy Token (single credential) @@ -42,1 +40,0 @@ -Use a proxy token for one specific credential. Get it by assigning a credential to an agent in the [dashboard](https://app.agentkeys.io). @@ -57,1 +54,0 @@ -### With Proxy Token (Option B) — direct credential access @@ -78,1 +74,0 @@ -1. Agent sends request to AgentKeys proxy with API key + credential name (or proxy token)
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.2.0. 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: agentkeys: Credential pass-through configuration (KillerSkills verdict caution 60)
## 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 60/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/agentkeys/1.2.0 ## Findings with a location - `SKILL.md:35` · Credential pass-through configuration — SKILL.md:35 · Credential pass-through configuration — agent relays sensitive credentials - `SKILL.md:42` · Credential pass-through configuration — SKILL.md:42 · Credential pass-through configuration — agent relays sensitive credentials - `SKILL.md:57` · Credential pass-through configuration — SKILL.md:57 · Credential pass-through configuration — agent relays sensitive credentials - `SKILL.md:14` · Credential pass-through configuration — SKILL.md:14 · Credential pass-through configuration — agent relays sensitive credentials - `SKILL.md:78` · Credential pass-through configuration — SKILL.md:78 · Credential pass-through configuration — agent relays sensitive credentials ## 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._
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.