project-init
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard command-line tools such as
ls,mkdir,grep, and the GitHub CLI (gh) to perform its initialization tasks. These operations are limited to the local project directory and the user's GitHub account. - [EXTERNAL_DOWNLOADS]: No external downloads or remote scripts were detected. The skill interacts solely with the user's GitHub environment via the authenticated
ghCLI. - [DATA_EXFILTRATION]: The skill reads project-specific files like
okr.mdandtasks.mdto avoid overwriting existing data. It does not access sensitive system files (e.g.,.ssh,.env,.aws/credentials) or send data to unauthorized external domains. - [PROMPT_INJECTION]: No malicious prompt injection patterns or attempts to bypass agent safety guidelines were found. The skill follows a structured, multi-phase guided workflow.
Audit Metadata