Skills
skills/builderio/agent-native/deck-management/Gen Agent Trust Hub

deck-management

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains informational documentation regarding the deck management schema and uses standard, project-internal CLI commands for database operations.
  • [PROMPT_INJECTION]: The documentation defines a schema that stores HTML content within the database, which identifies a potential surface for indirect prompt injection if the agent processes untrusted data from the slides. This is a characteristic of the documented data structure rather than a malicious instruction.
  • Ingestion points: The data column in the decks SQL table, accessed via the provided CLI and API examples.
  • Boundary markers: None specified in the documentation.
  • Capability inventory: The agent has SQL execution capabilities via the pnpm action db-exec tool.
  • Sanitization: The documentation does not specify sanitization procedures for the slide HTML content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 04:51 AM
Security Audit — agent-trust-hub — deck-management