event-speaker-kit
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill follows best practices for AI agent instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill addresses the risk of indirect prompt injection by explicitly instructing the agent to treat all content from fetched pages, uploaded files, or third-party text as data rather than instructions. It includes a specific protocol to report and ignore any embedded instructions.
- [COMMAND_EXECUTION]: The skill utilizes a local Python utility (
scripts/text_check.py) to perform deterministic checks on dates and character counts. This script uses only standard libraries and operates on files provided by the agent, posing no security risk in this context. - [DATA_EXFILTRATION]: The skill includes instructions to identify and report potential scams (e.g., requests for bank or tax details) found in event-related materials, protecting the user from exfiltration attempts by third parties.
Audit Metadata