harness-genome
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute the metaharness genome command, which is the primary mechanism for its repository analysis function.
- [EXTERNAL_DOWNLOADS]: The skill uses npx to retrieve and run the metaharness package from the NPM registry; this is a common practice for executing Node.js-based utilities without global installation.
- [PROMPT_INJECTION]: As the skill parses repository content at a provided path, it is subject to indirect prompt injection if a malicious repository contains data designed to bias the agent's report. 1. Ingestion points: Files at the user-specified path. 2. Boundary markers: None present. 3. Capability inventory: Bash shell access and npx package execution. 4. Sanitization: No sanitization of ingested repository data is mentioned.
Audit Metadata