meeting-prep
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill researches meeting attendees by ingesting data from external, untrusted sources such as LinkedIn, X (formerly Twitter), and various blogs or company websites. This content is then summarized and incorporated into a briefing. A malicious actor could embed instructions in their public profiles or articles to attempt to influence the agent's output.
- Ingestion points: Web search results and full-page extractions from social platforms and domains identified in
references/attendee-research.md(LinkedIn, x.com, github.com, etc.). - Boundary markers: The skill lacks explicit instructions to treat external data as untrusted or to wrap it in specific delimiters to prevent instruction leakage.
- Capability inventory: The agent has the ability to read and write to the local workspace (
people/andcompanies/directories) and perform web searches. - Sanitization: No specific sanitization or filtering logic is defined for the content extracted from external URLs.
Audit Metadata