co-ceo

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions and Markdown configuration. It defines a persona for business review and does not request or use any external tools, scripts, or network capabilities.
  • [NO_CODE]: There are no executable scripts, binaries, or code snippets included in this skill. All logic is handled through the large language model's inherent reasoning based on the provided instructions.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to analyze data provided by the user (plans, strategies, products). This represents a potential surface for indirect prompt injection if the user-provided content contains instructions designed to manipulate the agent.
  • Ingestion points: User-provided business plans, strategies, and product descriptions shared during the interaction (SKILL.md).
  • Boundary markers: Absent. The instructions do not define specific delimiters to wrap or isolate user input.
  • Capability inventory: None. The skill does not have access to file systems, network operations, or shell execution across its instructions.
  • Sanitization: Absent. There are no instructions for the agent to sanitize or validate the content of the user's plan before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 06:56 PM
Security Audit — agent-trust-hub — co-ceo