telegram-send

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses sensitive local file paths to manage authentication, including the Telegram session file at $SALES_PATH/telegram/sessions/telegram_session.session and environment variables in $SALES_PATH/.env. These files contain credentials and session tokens required for the skill's primary function.
  • [COMMAND_EXECUTION]: The skill invokes local Python scripts, specifically $TG_TOOLS_PATH/tools/tg_send.py, to process data and interact with the Telegram API.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted external data.
  • Ingestion points: Data enters the agent context via CSV files (e.g., contacts.csv) provided as input to the sending tool.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands within the CSV data are present in the skill definition.
  • Capability inventory: The skill can execute local Python scripts and perform network operations via the Telegram API to send messages to external recipients.
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the content provided in the CSV fields before it is interpolated into message templates.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 03:06 PM
Security Audit — agent-trust-hub — telegram-send