add-telegram
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches and merges code from the author's GitHub repository at
https://github.com/qwibitai/nanoclaw-telegram.git. This is a vendor-owned resource used to provide the Telegram channel implementation. - [COMMAND_EXECUTION]: The skill executes system-level commands to manage the integration, including environment variable configuration and service restarts using
launchctlorsystemctl. It also usesnpxto execute local setup scripts andnpmfor dependency management. - [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface as the agent is designed to process external messages from the Telegram channel.
- Ingestion points: External messages are received and processed via
src/channels/telegram.ts. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat incoming message content as untrusted data.
- Capability inventory: The agent has access to file system operations, package management, and service control commands through the skill's implementation.
- Sanitization: There is no evidence of sanitization or validation logic for the content of incoming Telegram messages in the provided skill definition.
Audit Metadata