find-simplifications
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the shell command
pnpm change:scope --base <verified-ref>. This is a standard operation within the Cherry Studio development workflow used to scope the audit to a specific branch or reference.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes external project data, including architecture/reference documentation and existing agent notes, which constitutes an attack surface for indirect prompt injection.\n - Ingestion points: Root instructions, architecture docs, reference docs, and active Agent Notes.\n
- Boundary markers: No specific boundary markers or 'ignore' instructions for the ingested content are defined.\n
- Capability inventory: The skill possesses the ability to read project files and execute local shell commands via the pnpm package manager.\n
- Sanitization: The instructions do not specify any sanitization or validation processes for the data retrieved from external project files.
Audit Metadata