manage-members

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute a local Python script (send.py) via the uv run command. This is used to perform administrative tasks such as inviting, kicking, and listing members in Telegram groups.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It retrieves information from an external source (Telegram member lists and search results) and displays it within the agent's context. An attacker could potentially embed instructions in their Telegram display name or username to influence the agent's behavior.
  • Ingestion points: Data returned by the members subcommand, including names and usernames from Telegram.
  • Boundary markers: No specific delimiters or instructions are provided to the agent to ignore or isolate content found in the Telegram member data.
  • Capability inventory: The skill has access to Bash (command execution), Read (file access), Grep, and Glob.
  • Sanitization: There is no evidence of sanitization or filtering of the member data before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 09:52 AM