run-aiewf-2024-evals
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown files that provide structured instructions and references. It does not contain any scripts, executables, or automated installers.
- [COMMAND_EXECUTION]: The README and SKILL.md files provide example
cpcommands for manual installation. These are local file system operations intended for the user and do not involve privilege escalation or suspicious behavior. - [EXTERNAL_DOWNLOADS]: The skill references the author's GitHub repository and a public YouTube playlist for educational context. These are well-known services and the references are informational, not involving runtime code retrieval.
- [DATA_EXFILTRATION]: No network activity, hardcoded credentials, or access to sensitive local files (such as SSH keys or environment variables) were found.
- [PROMPT_INJECTION]: The skill contains instructional constraints (e.g., "Do not summarize talks") to ensure the agent follows the intended workflow. These are standard task-specific instructions and do not attempt to bypass agent safety filters or override core system behavior.
Audit Metadata