telegram-groups

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a Python script located at $TG_TOOLS_PATH/tools/tg_groups.py to perform Telegram management tasks. The commands are executed locally using the system's python3 interpreter with arguments provided through the command line. This is the primary intended functionality of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted data by reading from external files (e.g., msg.txt for message content, users.csv for member lists) and by listing group members or group names from Telegram.
  • Ingestion points: Input files (msg.txt, users.csv) and output from the list and members commands (SKILL.md).
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Execution of the Python management script (SKILL.md).
  • Sanitization: Not explicitly mentioned; behavior depends on the implementation of the tg_groups.py script and the agent's command execution environment.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 02:05 PM
Security Audit — agent-trust-hub — telegram-groups