thread-summarizer
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data (email threads) which presents a standard indirect prompt injection surface.
- Ingestion points: The skill accepts a "full email thread" as the primary data source in SKILL.md.
- Boundary markers: The instructions do not define clear delimiters or boundary markers to separate the untrusted email content from the system instructions.
- Capability inventory: The skill has no tools, code execution capabilities, or network access, which significantly limits the potential impact of an injection attack.
- Sanitization: There is no logic provided to sanitize or filter the email content before it is processed by the AI.
Audit Metadata