digest
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection Surface]: The skill aggregates activity data from external, untrusted communication and storage channels to compile a summary digest.
- Evidence: Section 3 specifies gathering text content from
~~chat,~~email,~~cloud storage,~~project tracker,~~CRM, and~~knowledge baseinSKILL.md. - Context: External inputs like email bodies or chat messages could potentially contain text designed to influence the final presentation or formatting of the digest. However, the skill's capability inventory is limited to text generation, with no file system writes or unauthorized network operations, which minimizes potential impact. There are currently no explicit boundary markers or content sanitization steps detailed in the instructions.
Audit Metadata