ego-lite-simplify
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute several shell commands for repository analysis and verification, including
git status,rg(ripgrep),npm test,npm run e2e, andnpm run validate:site-skills. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it reads and processes external, potentially untrusted data from the repository it is tasked to simplify.
- Ingestion points: Repository source code files (
package/ego-browser/src),git statusoutput, documentation files, and symbol search results fromrg(SKILL.md). - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the files being analyzed.
- Capability inventory: The skill allows file system modification, execution of repository-defined test scripts (
npm test), and git command execution (SKILL.md). - Sanitization: There are no explicit instructions for the agent to sanitize or escape content read from the repository before processing it.
Audit Metadata