master-orchestrator
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to execute local scripts using shell commands such as
npm run skill:masterandnpx ts-node src/master.ts. - [DATA_EXFILTRATION]: The skill requires access to sensitive environment variables, specifically
ANTHROPIC_API_KEY, which is loaded from a local.envfile. - [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) due to its workflow design:
- Ingestion points: Automatically fetches untrusted content from the TopHub hot rankings service.
- Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore embedded commands within the fetched data.
- Capability inventory: The skill possesses network access (TopHub), file system write capabilities (
outputs/directory), and local command execution (ts-node). - Sanitization: There is no mention of sanitizing or validating the content retrieved from TopHub before it is passed to the LLM for content generation.
Audit Metadata