tg-reply-rewrite
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and rewrite untrusted data such as raw logs, agent replies, and status reports.
- Ingestion points: Technical logs and agent output provided as input for rewriting (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' commands to prevent the agent from obeying instructions that might be embedded in the raw technical logs.
- Capability inventory: The skill is capable of generating formatted HTML and Markdown for Telegram delivery via the referenced 'tg-rich-messages' tool.
- Sanitization: The skill provides guidance on escaping HTML entities to prevent malformed message structure.
- [SAFE]: The skill includes an explicit security rule (Rule 9) to identify and remove sensitive data like tokens, passwords, and private keys from the final output.
Audit Metadata