resonance-designer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection surface detected in
scripts/search.py. \n - Ingestion points: The script queries local design documentation and returns it to the agent context. \n
- Boundary markers: Absent. The search results are returned as raw text without delimiters to separate untrusted data from system instructions. \n
- Capability inventory: The skill possesses powerful tools (
run_command,write_file,edit_file), which could be misused if the agent is influenced by instructions hidden in search data. \n - Sanitization: Absent. The search script truncates output but does not sanitize for embedded prompt overrides or code. \n- [COMMAND_EXECUTION] (SAFE): The skill correctly requests
run_commandfor its intended role as a design system architect; no malicious command patterns were found in the provided source files.
Audit Metadata