extension-analyze
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the AI agent to execute shell commands, including
ls,cat,grep,jq, andnpm audit, to inspect the file system and audit the contents of a Chrome extension project directory. - [INDIRECT_PROMPT_INJECTION]: The skill has an inherent attack surface for indirect prompt injection because its primary function is to read and analyze untrusted external data (extension source code and configuration files).
- Ingestion points: The agent is directed to read the
manifest.jsonfile and various source files (e.g.,.tsand.jsfiles) within the extension's directory (SKILL.md, Steps 2-5). - Boundary markers: The skill does not provide explicit markers or instructions to help the agent distinguish between the extension's content and its own operational instructions.
- Capability inventory: The agent uses shell command execution (bash) to perform the audit workflow.
- Sanitization: The skill lacks mechanisms to sanitize the content of the files being read before the agent processes them.
Audit Metadata