← agent-phone-call@1.0.5

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. 79 · Caution

Evidence

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

Diff · removes 6 caught lines

Download .patch
diff --git a/scripts/activation.sh b/scripts/activation.sh
--- a/scripts/activation.sh
+++ b/scripts/activation.sh
@@ -15,1 +15,0 @@
-# Read token from credentials file (never pass token as CLI arg)
diff --git a/scripts/balance.sh b/scripts/balance.sh
--- a/scripts/balance.sh
+++ b/scripts/balance.sh
@@ -15,1 +15,0 @@
-# Read token from credentials file (never pass token as CLI arg)
diff --git a/scripts/prompt_update.sh b/scripts/prompt_update.sh
--- a/scripts/prompt_update.sh
+++ b/scripts/prompt_update.sh
@@ -20,1 +20,0 @@
-# Read token from credentials file (never pass token as CLI arg)
diff --git a/scripts/inbound.sh b/scripts/inbound.sh
--- a/scripts/inbound.sh
+++ b/scripts/inbound.sh
@@ -13,1 +13,0 @@
-# Read token from credentials file (never pass token as CLI arg)
diff --git a/scripts/query.sh b/scripts/query.sh
--- a/scripts/query.sh
+++ b/scripts/query.sh
@@ -14,1 +14,0 @@
-# Read token from credentials file (never pass token as CLI arg)
diff --git a/scripts/send.sh b/scripts/send.sh
--- a/scripts/send.sh
+++ b/scripts/send.sh
@@ -20,1 +20,0 @@
-# Read token from credentials file (never pass token as CLI arg)

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.5. 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-phone-call: Credential pass-through configuration (KillerSkills verdict caution 79)

## 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 79/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/agent-phone-call/1.0.5

## Findings with a location
- `scripts/activation.sh:15` · Credential pass-through configuration — scripts/activation.sh:15 · Credential pass-through configuration — agent relays sensitive credentials
- `scripts/balance.sh:15` · Credential pass-through configuration — scripts/balance.sh:15 · Credential pass-through configuration — agent relays sensitive credentials
- `scripts/prompt_update.sh:20` · Credential pass-through configuration — scripts/prompt_update.sh:20 · Credential pass-through configuration — agent relays sensitive credentials
- `scripts/inbound.sh:13` · Credential pass-through configuration — scripts/inbound.sh:13 · Credential pass-through configuration — agent relays sensitive credentials
- `scripts/query.sh:14` · Credential pass-through configuration — scripts/query.sh:14 · Credential pass-through configuration — agent relays sensitive credentials
- `scripts/send.sh:20` · Credential pass-through configuration — scripts/send.sh:20 · Credential pass-through configuration — agent relays sensitive credentials

## Proposed change
The attached patch removes the 6 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._
No GitHub source is recorded for this package, so there is nothing to open; paste the body into the registry's support channel.

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.