database-documentation-gen

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes database metadata (table/column comments and definitions) which serves as an ingestion point for untrusted data, creating a surface for indirect prompt injection.
  • Ingestion points: Database schema metadata retrieved via psql and mysql CLI tools as described in SKILL.md.
  • Boundary markers: Absent; the instructions do not provide delimiters or specific guidelines to ignore instructions that might be embedded within the metadata.
  • Capability inventory: The agent has access to Bash, Read, Write, and Edit tools to process the data and save documentation files.
  • Sanitization: No sanitization or validation of the retrieved database metadata is performed before it is formatted into Markdown output.
  • [COMMAND_EXECUTION]: The skill requires the execution of database-specific CLI tools (psql, mysql, mongosh) to perform introspection. While necessary for the skill's purpose, this represents a significant command execution surface. Security is managed through the use of specific tool prefixes in the allowed-tools configuration to restrict the scope of shell access.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 08:02 AM