babylon-help
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to interact with the project environment. This includes running
npm installto manage dependencies and usingrg(ripgrep) to search through the contents ofnode_modulesand local source files. - [EXTERNAL_DOWNLOADS]: The skill facilitates the download of external Node.js packages. If the
node_modulesdirectory is not found, the agent is directed to runnpm install, which fetches packages from the npm registry. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing untrusted project data.
- Ingestion points: The agent reads and interprets the content of
package.json,package-lock.json, and the source/types files within thenode_modulesdirectory (SKILL.md). - Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore potential commands embedded within the project files it analyzes.
- Capability inventory: The agent can execute shell commands (
npm install,rg) and perform local file writes (appending to./.babylon-help.log). - Sanitization: Absent. There is no mention of validating or escaping the content retrieved from external files before it is used to influence the agent's behavior or output.
Audit Metadata