investor-updates-skill

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a workflow for processing potentially untrusted data from external sources, which creates a surface for indirect prompt injection attacks.
  • Ingestion points: The skill instructions specify pulling data from connected CRMs (investor notes), knowledge bases (prior updates), and BI/spreadsheets (financial metrics).
  • Boundary markers: No explicit delimiters (like XML tags or triple quotes) or specific instructions are provided to help the agent distinguish between its core instructions and data retrieved from these tools.
  • Capability inventory: The skill is focused on text generation and drafting; it does not explicitly define capabilities for shell command execution, direct file system writes, or external network operations beyond the tool placeholders.
  • Sanitization: There are no instructions for sanitizing or validating the retrieved data before it is incorporated into the drafted update.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 11:32 AM
Security Audit — agent-trust-hub — investor-updates-skill