the-90-second-brief
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's functionality is limited to collecting and summarizing publicly available company data. No evidence of credential theft, unauthorized file access, or persistence mechanisms was found.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from external websites using WebSearch and WebFetch (Ingestion points: SKILL.md research section). There are no specific boundary markers or sanitization procedures mentioned to differentiate between site content and agent instructions. However, the risk is negligible as the skill's capabilities are restricted to text generation, with no ability to execute commands, write files, or perform network exfiltration based on the gathered data.
Audit Metadata