telegram
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
npx @useclawlink/clito interact with the Telegram API. These commands are provided by the official vendor and author of the skill (clawlink-hq) and are used for legitimate setup and messaging actions.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes messages from external Telegram users. - Ingestion points: External data is ingested into the agent context via the
telegram_get_chat_historyandtelegram_get_updatestools. - Boundary markers: The instructions do not define specific delimiters or instructions to treat external message content as untrusted data.
- Capability inventory: The agent has the capability to execute CLI commands and perform write operations (e.g., sending messages, deleting messages) based on the processed data.
- Sanitization: The skill description does not specify any sanitization or filtering of the message text retrieved from the Telegram API.
Audit Metadata