The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script named send.py using the uv tool. This script is intended to facilitate interaction with Telegram services and is located within the plugin's environment paths.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from Telegram chat messages. If a message contains adversarial instructions, the agent might follow them while processing the chat history.
Ingestion points: The skill retrieves chat messages using the read command, bringing external content into the agent's context.
Boundary markers: No specific delimiters or instructions are used to distinguish between chat content and agent instructions.
Capability inventory: The skill uses the Bash tool to run shell commands and the send.py script to perform network and file operations.
Sanitization: There is no evidence of sanitization or filtering applied to the messages fetched from Telegram.

download-media