The Agent Skills Directory

Data Exposure (HIGH): The skill explicitly accesses .env files and reads high-value secrets including TELEGRAM_API_ID, TELEGRAM_API_HASH, and TELEGRAM_SESSION. According to security standards, accessing sensitive file paths such as environment configuration files is a high-risk activity that can lead to credential theft.
Credentials Access (HIGH): The tool is designed to retrieve and validate the format/length of authentication tokens. This behavior provides a direct mechanism for an AI agent to access account-level secrets, which could be exfiltrated if the agent is compromised or subjected to a prompt injection attack.
Indirect Prompt Injection (LOW):
Ingestion points: The tool reads from local configuration files: .env and config/agents.yaml (File: SKILL.md).
Boundary markers: No delimiters or safety instructions are specified for handling the content of these files.
Capability inventory: The underlying script (telegram_doctor.py) has the capability to initiate network connections to the Telegram API (File: SKILL.md).
Sanitization: No evidence of sanitization or validation of the input data is provided in the skill documentation.

telegram-doctor