CampaignsAI plugin / MCP / skill
hackerbot-claw: self-described AI agent exploiting GitHub Actions and poisoning CLAUDE.md
- Status unknownWe can't confirm whether this has been taken down. Treat it as possibly live. Status checked .
- Moderate confidence
- Indicators (3): CSV, JSON
- Seen to
Do this now
- Remove pull_request_target workflows that check out untrusted code; sanitize branch and file names used in scripts
- Make AI review workflows read CLAUDE.md and similar context files from the base branch only, with least-privilege tokens
- Block the listed domains and rotate tokens exposed to fork-PR workflows
Indicators to check
Look for any of these on your machines or in your logs:
- repository
github[.]com/hackerbot-claw
What happened
A GitHub account describing itself as an autonomous agent attacked CI workflows in several large open-source projects using pwn-request, branch-name, filename and script injection. It got code execution in several repos and stole a write-scoped token from one. In another repo it replaced CLAUDE.md with injected instructions aimed at an AI review workflow, which the model flagged and refused.
- Claude Code
- GitHub Actions
Attack chain
-
Lure
Malicious pull requests and a poisoned agent context file (CLAUDE.md)
First seen
-
Artifact
Crafted PRs and branch names; modified CLAUDE.md
-
Actor
No source we cite attributes this activity to an actor.
-
Infrastructure
- Payload hosting and exfil domain
Last seen
Timeline
- First seen
- StepSecurity reports
- Last seen
- Status checked: Status unknown
Related campaigns
| Type | Value | Copy |
|---|---|---|
| domain | hackmoltrepeat[.]com | |
| domain | recv[.]hackmoltrepeat[.]com | |
| repository | github[.]com/hackerbot-claw |
Confidence: Moderate
Strong evidence, not yet confirmed by our own analysis. See the confidence scale for what each level requires. The sources below are the evidence.
Sources
Notes
- Mostly CI exploitation rather than social engineering; included for the agent-context poisoning attempt.
Corrections
No corrections.
See the corrections policy. Spotted an error? Tell us.