telegram-openapi-skill
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches a curated OpenAPI schema from the holon-run GitHub repository to define Telegram Bot API operations for the uxc tool.
- [SAFE]: Implements secure credential handling by using environment variables for bot tokens and providing path-prefix templates for request authentication.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Telegram updates. 1. Ingestion points: post:/getUpdates in SKILL.md and usage-patterns.md. 2. Boundary markers: instructions to focus automation on JSON output and parse stable envelope fields. 3. Capability inventory: messaging operations (sendMessage, sendPhoto, etc.) and webhook management. 4. Sanitization: includes explicit guardrails requiring human-in-the-loop confirmation before any write or high-risk action is performed.
Audit Metadata