ceo-advisor

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (scripts/strategy_analyzer.py and scripts/financial_scenario_analyzer.py) for strategic analysis and financial modeling. These scripts are provided as part of the skill's functional toolkit.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface due to its data ingestion practices.
  • Ingestion points: The skill explicitly reads 'company-context.md' to incorporate organization-specific data into the agent's context before responding.
  • Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to treat the content of 'company-context.md' as untrusted data or to ignore instructions embedded within it.
  • Capability inventory: The agent has the capability to execute local analysis scripts and invoke other agent roles via a specific custom syntax ([INVOKE:role|question]).
  • Sanitization: Absent. There is no evidence of sanitization, validation, or filtering of the content read from the context file before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:07 PM
Security Audit — agent-trust-hub — ceo-advisor