draft-message

Fail

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill contains a hardcoded Telegram API_ID (18256514) and API_HASH (4b812166a74fbd4eaadf5c4c1c855926) within the Python scripts provided in the instructions.
  • [CREDENTIALS_UNSAFE]: The skill explicitly accesses sensitive Telegram session data located at ~/.local/share/telethon/eon. These files contain active authentication tokens that could be compromised if accessed by unauthorized processes.
  • [EXTERNAL_DOWNLOADS]: The skill uses the uv tool to download and install the telethon package from the Python Package Index (PyPI) at runtime without specifying a version, which introduces supply chain risks.
  • [COMMAND_EXECUTION]: The skill generates and executes Python code dynamically using bash heredocs (PYEOF and DRAFT_EOF). This pattern is often used to execute logic that bypasses static analysis.
  • [DATA_EXFILTRATION]: While the stated purpose is sending to 'Saved Messages', the skill facilitates the transmission of local data and user-provided content to external Telegram servers using authenticated sessions.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts a message parameter that is interpolated into a script and transmitted to an external service.
  • Ingestion points: The message argument in the tg-cli.py draft command and the BODY variable in the Direct Telethon section of SKILL.md.
  • Boundary markers: Absent. The content is directly embedded into script strings.
  • Capability inventory: The skill uses uv run for subprocess execution, os.path.expanduser for file system access, and telethon for network communication.
  • Sanitization: None detected. The skill allows raw HTML input through the --html flag without validation or escaping.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
May 11, 2026, 01:10 AM