chatexport-need-miner
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Telegram chat histories, creating a surface for indirect prompt injection.
- Ingestion points: Data enters the agent via the result.json file mining logic defined in SKILL.md.
- Boundary markers: The skill does not prescribe specific delimiters to distinguish between extracted verbatim quotes and agent instructions.
- Capability inventory: The skill is scoped for use with advanced LLMs that typically have file and shell access.
- Sanitization: No sanitization or escaping of the raw message text is performed before it is presented to the model.
Audit Metadata