meeting-briefing
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is composed exclusively of Markdown instructions, methodology descriptions, and response templates. It does not include any Python scripts, Node.js code, shell scripts, or other executable components.
- [SAFE]: Evaluation of the skill's instructions revealed no attempts at prompt injection, obfuscation, or unauthorized data access. The methodology described follows standard administrative and legal support practices.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a data aggregator, which creates a surface for indirect instructions to be processed from external sources.
- Ingestion points: Untrusted data enters the agent's context through connected systems identified in Step 3, including Email, Chat (Slack/Teams), Documents (Box/Egnyte/SharePoint), and CRM/CLM systems.
- Boundary markers: Absent. The skill does not instruct the agent to use specific delimiters or to disregard potential commands found within the processed materials.
- Capability inventory: No capabilities such as file-writing, network requests, or command execution are requested or defined within this specific skill file.
- Sanitization: There are no instructions for sanitizing or escaping the content retrieved from external sources before it is synthesized into the briefing template.
Audit Metadata