official-hotkey-ingestion

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is designed to search and retrieve data from official vendor documentation and websites. This external data fetching is the primary purpose of the skill and is controlled by a structured discovery process to ensure source legitimacy.
  • [COMMAND_EXECUTION]: The agent generates SQL statements for execution via a PostgreSQL MCP tool. This capability is safeguarded by requiring the agent to present a full plan and SQL skeleton to the user for approval before any database operations are performed.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection through the documentation it scrapes. Ingestion points: Official documentation websites retrieved during execution. Boundary markers: No specific delimiters or safety instructions are defined for the scraped content. Capability inventory: Database write operations through the PostgreSQL MCP. Sanitization: Mitigated by the requirement for human verification of the generated SQL plans.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 09:39 AM