meeting-briefing-anthropic
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown documentation and instructions. No executable scripts or code files are present in the skill bundle.
- [PROMPT_INJECTION]: The skill establishes a workflow for processing data from external, untrusted sources such as email and chat, creating an indirect prompt injection surface. 1. Ingestion points: Untrusted data enters the agent context via Email, Chat, and Document sources (SKILL.md). 2. Boundary markers: No delimiters or safety instructions are provided to distinguish ingested content from system instructions. 3. Capability inventory: The skill contains no scripts, shell commands, or network operations. 4. Sanitization: There are no instructions for sanitizing or escaping the content retrieved from external sources.
Audit Metadata