specs-db

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local documentation to generate database structures, which is an inherent part of its design functionality.
  • Ingestion points: Processes docs/product/business-flow.md, docs/product/demo/ (HTML pages), and docs/product/glossary.md in SKILL.md.
  • Boundary markers: No specific delimiters or "ignore" instructions are used for the content of these documentation files.
  • Capability inventory: The skill performs directory creation (mkdir) and writes schema files (table.sql or schema.json) to the local file system.
  • Sanitization: No explicit sanitization of the documentation content is mentioned before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill uses standard shell commands to manage the project structure.
  • Evidence: Executes mkdir -p docs/specs/data within SKILL.md to ensure the target output directory exists.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 02:49 PM
Security Audit — agent-trust-hub — specs-db