telegram

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the Telegram API, creating a surface for indirect prompt injection. External messages are written to a shared inbox file and subsequently read by the agent.
  • Ingestion points: telegram_check.py and telegram_callback.py read message text and callback data from ~/.claudicle/daemon/inbox.jsonl.
  • Boundary markers: The skill documentation mentions sanitization but does not show explicit boundary delimiters in the script logic for inbox reading.
  • Capability inventory: The skill can send messages via telegram_send.py and manage bot memory state through telegram_memory.py.
  • Sanitization: SKILL.md states that user-provided text is sanitized for XML tags before being processed by the cognitive pipeline.
  • [DYNAMIC_EXECUTION]: The telegram_memory.py script performs dynamic loading of modules by modifying the Python path at runtime.
  • Evidence: The script uses sys.path.insert to include local directories such as ~/.claudicle/adapters/shared, ~/.claudicle/daemon, and ~/.claude/skills/shared to import internal framework components like claudicle_memory and usermodel_resolver.
  • [COMMAND_EXECUTION]: The skill's architecture relies on the execution of multiple discrete Python scripts via subprocess calls to handle Telegram interactions.
  • [EXTERNAL_DOWNLOADS]: The skill requires external Python libraries to function.
  • Evidence: Documentation specifies prerequisites including requests for the REST-based scripts and python-telegram-bot for the optional listener component.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 06:34 PM