The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the '@cyberdrk/tg' package and suggests cloning from 'https://github.com/cyberdrk305/telegram.git', which are resources provided by an unverified third-party author.
[REMOTE_CODE_EXECUTION]: Installation and usage of the CLI tool involves downloading and executing code from an external, non-trusted repository and package registry.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by retrieving and processing untrusted content from Telegram messages. 1. Ingestion points: Data enters the agent's context through the 'tg read', 'tg inbox', and 'tg search' commands. 2. Boundary markers: The skill does not define specific delimiters or instructions to help the agent distinguish between message content and legitimate commands. 3. Capability inventory: The skill permits the agent to send and reply to messages, providing a path for malicious instructions to trigger outbound actions. 4. Sanitization: There is no evidence of input validation, filtering, or sanitization of the external message content before it is processed.

tg