ddg-agent-security-sweep

• Outcome: Review
• Latest audit: Oct 22, 2026 · 11:27 PM UTC
• Version: 1.0.0

Overview

This security-scanning workflow needs review because it directs the agent to retain potentially confidential scan requests in the repository without storage safeguards.

Review and redact submissions before sending them to DDG, and check the provider’s data-handling terms. Keep retry payloads in restricted temporary storage outside the repository, exclude reports from version control, and delete temporary data afterward. Set an explicit spending limit before enabling paid retries.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Output Handling: Unvalidated Output Injection, Cross-Context Output, Unbounded Output
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Credential Access

High

• Category: Privilege Escalation
• Confidence: 70% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 73)May include surrounding context.

bash

   curl -s -X POST https://agents.daedalusdevelopmentgroup.com/v1/secret-leak-api-key-scan \
     -H 'content-type: application/json' -H "X-Agent-Id: $DDG_AGENT_ID" \
     -d '{"content":"<file or diff text>"}' > out/secrets.json

Findings are returned redacted; rotate anything in leak_paths. 4. Dependency risk — one call with the manifest body:

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 60% confidence

Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md

openclaw:
    requires:
      bins:
        - curl
    envVars:
      - name: DDG_AGENT_ID
        required: false

The retry workflow instructs the agent to retain scan payloads in the repository without warning about sensitive-data persistence.

Medium

• Category: Output Handling
• Confidence: 96% confidence

Finding

The instruction to keep the sweep body in the repository can persist confidential system prompts, internal tool descriptions, configuration, logs, or accidentally included credentials. The later warning against sending production secrets reduces some risk but does not address repository persistence, where committing or publishing these payloads could expose them through version history.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.