daily-life-discovery

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided conversational data and uses it to drive agent inspections and the generation of new tools.\n
  • Ingestion points: Interactive user dialogue guided by instructions in SKILL.md and references/question-bank.md.\n
  • Boundary markers: Includes explicit privacy gates and consent protocols to prevent unauthorized data storage or action.\n
  • Capability inventory: The agent is instructed to perform discovery on host tools, memory, and CLIs, and may propose the creation of new scripts or skills.\n
  • Sanitization: The instructions do not specify technical details on how the agent should filter or sanitize user input before using it to generate CLI tools or skills.\n- [DYNAMIC_EXECUTION]: The skill facilitates the creation and testing of new executable artifacts based on user requirements.\n
  • Evidence: In SKILL.md, the agent is encouraged to build 'portable skills' or 'focused CLI tools' to address recurring needs, which involves runtime code generation and subsequent execution possibilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 05:58 PM
Security Audit — agent-trust-hub — daily-life-discovery