audit
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes several CLI tools to analyze and update the project environment, including
pnpm audit,pnpm why,pnpm outdated,pnpm info,pnpm update, andgrep. These are standard tools for the task described.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external tools and services, creating a surface for indirect prompt injection where malicious data could influence agent behavior.\n - Ingestion points: Untrusted data enters the agent context through the JSON output of
pnpm auditand search results fromgh search issues.\n - Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the ingested data.\n
- Capability inventory: The agent can execute package management commands (
pnpm update) and perform network searches (gh search) based on the data processed.\n - Sanitization: Absent. The skill provides no instructions to sanitize or validate external inputs (such as package names or repository identifiers) before they are interpolated into shell commands.
Audit Metadata