adopt
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to scan vault structures and manage system configurations. It generates a local shell script at
.claude/hooks/adopt-env.shto store folder mappings and updates thesession-init.shfile to source this configuration, ensuring environment variables persist across sessions. - [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it reads and parses the content of existing markdown files in the user's vault to identify organizational patterns. Ingestion points: The skill scans and greps through .md files during the vault structure analysis phase. Boundary markers: The skill does not implement explicit delimiters or instructions to ignore instructions embedded within the user's notes. Capability inventory: The skill has access to Read, Write, Edit, and Bash tools, allowing for file modification and command execution. Sanitization: Risk is reduced by the use of the AskUserQuestion tool, which requires the user to manually confirm or correct all detected folder mappings before any configuration is finalized.
Audit Metadata