live-web
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute a Python script located at
<MORU_ROOT>/scripts/path_claims.py. This script is used to perform several operations including checking claim status, claiming file paths for editing, verifying changes, and releasing claims. - [INDIRECT_PROMPT_INJECTION]: The skill processes 'Moru Inspect' reference lines which include visible text and CSS selectors extracted from live web pages. This creates an attack surface where malicious content on the inspected page could be ingested into the agent's context.
- Ingestion points: The inspection reference line pasted by the user (as described in SKILL.md), which includes the 'visible text' field.
- Boundary markers: None specified for the content of the reference line; the agent is instructed to read it left to right to find source files and components.
- Capability inventory: The skill possesses file system read/write capabilities (editing referenced files) and the ability to execute the
path_claims.pysubprocess. - Sanitization: No explicit sanitization or instruction to ignore embedded directives within the reference line data is provided.
Audit Metadata