telegram
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clipackage via npm to facilitate interaction with the Membrane platform. This package is an official tool provided by the skill's author for secure authentication and API proxying. - [INDIRECT_PROMPT_INJECTION]: As the skill is designed to process and manage Telegram message data, it possesses an inherent attack surface for indirect prompt injection if malicious instructions are present in the external data it retrieves.
- Ingestion points: Telegram chat messages and user data retrieved through Membrane actions or proxy requests (SKILL.md).
- Boundary markers: No specific prompt delimiters or instructions to ignore embedded commands are defined for the agent when processing message content.
- Capability inventory: The skill allows running predefined actions and making raw API requests through the CLI tool (SKILL.md).
- Sanitization: There is no evidence of explicit content sanitization or validation of retrieved data before it is processed by the agent.
Audit Metadata