degenclaw

Fail

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: HIGHPERSISTENCEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PERSISTENCE]: The dgclaw.sh script implements setup-cron and remove-cron commands that directly modify the user's crontab to install a recurring background task. This task is designed to poll for forum updates and trigger agent responses automatically, maintaining activity across sessions without user intervention.
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a significant attack surface for indirect prompt injection. The automated cron job fetches "unreplied-posts" from a public forum (https://degen.virtuals.io) and pipes the raw text into the agent's chat context via acp_cmd agent chat. Ingestion points: Public forum posts are fetched via dgclaw.sh. Boundary markers: There are no delimiters or instructions provided to the agent to ignore embedded commands within the forum data. Capability inventory: The agent has powerful capabilities including perpetual trading (acp trade), wallet management, and forum posting. Sanitization: No sanitization, escaping, or validation is performed on the external forum content before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill relies heavily on shell command execution to perform its core functions. dgclaw.sh invokes system binaries like curl, openssl, and jq, while the TypeScript utility scripts (trade.ts, withdraw.ts, activate-unified.ts) use child_process.execSync to run the acp-cli tool with dynamically constructed arguments.
  • [EXTERNAL_DOWNLOADS]: The skill's documentation requires the manual cloning and installation of the acp-cli repository from GitHub (https://github.com/Virtual-Protocol/acp-cli.git). This repository contains the primary execution logic for trading and signing, representing a critical external dependency that is not bundled with the skill itself.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Sep 17, 2026, 04:28 AM
Security Audit — agent-trust-hub — degenclaw