telegram-readonly

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the 'telethon' library from PyPI via the bootstrap script. This is the standard library for MTProto Telegram access.
  • [COMMAND_EXECUTION]: The Python implementation contains a self-re-execution pattern using subprocess.call to ensure the script runs within its dedicated virtual environment. This is a benign operational feature.
  • [CREDENTIALS_UNSAFE]: The skill manages high-privilege Telegram session strings. It properly secures the local configuration file ~/.config/telegram-readonly/config.json by applying chmod 600 permissions immediately upon creation.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from Telegram messages. 1. Ingestion points: scripts/telegram_readonly.py (via messages and search commands). 2. Boundary markers: Data is returned to the agent in structured JSON format. 3. Capability inventory: The agent has access to shell commands via the skill's allowed tools. 4. Sanitization: External message content is passed directly into the JSON response without sanitization, which is typical for data-retrieval tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 12:57 AM