board-deck-builder

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes updates from product, growth, finance, and execution teams. These external data sources can be used as vectors for indirect prompt injection, particularly as the agent has access to powerful tools.
  • Ingestion points: Described in the 'Purpose' section of SKILL.md as updates from various departments.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided for the ingestion process.
  • Capability inventory: The agent uses an ExecutionProxy Interface for shell command execution and a MemoryStore Interface for writing to the filesystem.
  • Sanitization: The 'Security & Multi-Agent Hygiene' section requires PII and secret redaction but does not address input validation or instruction filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:35 AM
Security Audit — agent-trust-hub — board-deck-builder