Back to skill

Security audit

Bounty Hunter Agent

Security checks for vulnerabilities and agentic risk

Overview

The scanner itself is mostly a GitHub bounty finder, but the skill advertises autonomous fix sessions and automatic PR submission without clear user controls.

Install only if you are comfortable giving the skill access to your authenticated GitHub CLI context. Treat the current script as a read-oriented bounty scanner, but review or disable any future OpenClaw fix-session or automatic PR workflow unless it requires explicit confirmation and clear repository boundaries.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill says it can 'spawn fix sessions' and integrate with OpenClaw to kick off autonomous coding sessions, but this high-impact autonomous behavior is not surfaced as a safety warning. In context, an agent that scans external targets and can automatically initiate coding work raises the risk of unintended actions, resource use, or unsafe downstream automation if users do not realize the behavior is available or enabled.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/bounty_scan.py (reported line 69)May include surrounding context.

python
if paginate:
        cmd.append("--paginate")
    try:
        result = subprocess.run(
            cmd, capture_output=True, text=True, timeout=30
        )
        if result.returncode != 0:

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/bounty_scan.py (reported line 88)May include surrounding context.

python
"--json", "repository,number,title,labels,url,createdAt,comments",
    ]
    try:
        result = subprocess.run(
            cmd, capture_output=True, text=True, timeout=60
        )
        if result.returncode != 0:

Session Persistence

Medium
Category
Rogue Agent
Confidence
55% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · scripts/bounty_scan.py (reported line 167)May include surrounding context.

python
def load_state() -> dict:
    """Load persisted state."""
    state_file = STATE_DIR / "bounties.json"
    if state_file.exists():
        try:

Tainted flow: 'state_file' from os.environ.get (line 181, credential/environment) → open (file write)

Medium
Category
Data Flow
Confidence
87% confidence
Finding

The write target is derived from BOUNTY_STATE_DIR, an environment variable, and the code writes to that path without validating that it stays within an expected safe directory. In environments where an attacker can influence environment variables, this can cause arbitrary file overwrite within the permissions of the running user, including clobbering sensitive dotfiles or agent state.

Content

Scanner excerpt · scripts/bounty_scan.py (reported line 182)May include surrounding context.

python
"""Persist state to JSON."""
    STATE_DIR.mkdir(parents=True, exist_ok=True)
    state_file = STATE_DIR / "bounties.json"
    with open(state_file, "w") as f:
        json.dump(state, f, indent=2, default=str)

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/bounty_scan.py (reported line 194)May include surrounding context.

python
print("🔍 Bounty Hunter Agent — Scanning for opportunities...\n")

    # Verify gh auth
    auth_check = subprocess.run(
        ["gh", "auth", "status"], capture_output=True, text=True
    )
    if auth_check.returncode != 0:

Session Persistence

Medium
Category
Rogue Agent
Confidence
55% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · scripts/bounty_scan.py (reported line 224)May include surrounding context.

python
print(f"\n📋 Found {len(raw_issues)} unique bounty-labeled issues\n")

    # Load previous state for dismissed issues
    state = load_state()
    dismissed = set(tuple(d) for d in state.get("dismissed", []))

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly states that it tracks state in a local JSON file, but the description does not present this as a persistence/privacy-relevant behavior or warn users that data about scanned opportunities will be written to disk. This is not code execution by itself, but undisclosed local persistence can surprise users, leave stale sensitive workflow data behind, and increase risk on shared or managed systems.

Content

No source excerpt is available for this finding.