supply-chain-harden
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to run
pnpm installandpnpm auditin the user's workspace. These commands execute shell processes and, in the case of installation, may trigger package lifecycle scripts that run arbitrary code. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it processes untrusted external data that then influences its actions and command execution.
- Ingestion points: The agent reads content from
pnpm-workspace.yaml,package.json, lockfiles, and results from web searches. - Boundary markers: The instructions do not specify any delimiters or safety markers to help the agent distinguish between data and potential instructions embedded within these files.
- Capability inventory: The skill has the capability to execute shell commands (
pnpm install,pnpm audit) based on the context it reads. - Sanitization: There is no mention of sanitization or validation for the configuration files or search results before they are used to determine configuration changes or command arguments.
Audit Metadata