capacitor-plugin-upgrade-v7-to-v8
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes load-time command execution (dynamic context injection) to inspect the local environment.\n
- File:
SKILL.md\n - Evidence:
!node -e "..."and!find . ...\n - Description: These commands extract package versions and directory structure to provide context for the upgrade process.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface.\n
- Ingestion points: Data from
package.json(name, version, dependencies) is read and injected directly into the prompt.\n - Boundary markers: Injected content is not wrapped in delimiters or safety instructions.\n
- Capability inventory: The skill has access to the
Bashtool, which could be abused if the injected project metadata contains malicious instructions.\n - Sanitization: No sanitization is performed on the data extracted from the external file.
Audit Metadata