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 5 caught lines
Download .patchdiff --git a/SKILL.md b/SKILL.md --- a/SKILL.md +++ b/SKILL.md @@ -561,1 +561,0 @@ -python scripts/telnyx_api.py create-mission <name> <instructions> @@ -582,1 +581,0 @@ -python scripts/telnyx_api.py create-assistant <name> <instructions> <greeting> [options_json] @@ -618,1 +616,0 @@ -python scripts/telnyx_api.py init <name> <instructions> <request> [steps_json] @@ -619,1 +616,0 @@ -python scripts/telnyx_api.py setup-agent <slug> <name> <instructions> <greeting> diff --git a/setup.sh b/setup.sh --- a/setup.sh +++ b/setup.sh @@ -64,1 +64,0 @@ -read -s -p "Enter your API key (or press Enter to skip for now): " api_key
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 2.0.5. 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: clawdtalk-client: Fake instruction boundary tag (KillerSkills verdict caution 72)
## 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 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/clawhub/clawdtalk-client/2.0.5 ## Findings with a location - `SKILL.md:561` · Fake instruction boundary tag — SKILL.md:561 · Fake instruction boundary tag - `SKILL.md:618` · Fake instruction boundary tag — SKILL.md:618 · Fake instruction boundary tag - `SKILL.md:582` · Fake instruction boundary tag — SKILL.md:582 · Fake instruction boundary tag - `setup.sh:64` · Prompting user to enter sensitive credentials — setup.sh:64 · Prompting user to enter sensitive credentials — social engineering - `SKILL.md:619` · Fake instruction boundary tag — SKILL.md:619 · Fake instruction boundary tag ## 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 team-telnyx/clawdtalk-client --clone && cd clawdtalk-client curl -s https://killerskills.ai/skills/clawhub/clawdtalk-client/2.0.5/patch.diff | git apply --unidiff-zero git checkout -b killerskills/2.0.5 && git commit -am "clawdtalk-client: Fake instruction boundary tag" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/clawdtalk-client/2.0.5/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.