schema-diff-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external database schema definitions, which creates an attack surface for indirect prompt injection where malicious instructions could be embedded in SQL comments or metadata to influence the agent's behavior.\n
- Ingestion points: Reads environment dumps, migration folders, and declarative definitions as described in SKILL.md.\n
- Boundary markers: No specific delimiters or warnings to ignore embedded instructions are present.\n
- Capability inventory: The skill writes reports and JSON output to the filesystem ('docs/database-report/') and manages workflow handoffs.\n
- Sanitization: The skill does not describe any validation or sanitization of the input schema data.\n- [EXTERNAL_DOWNLOADS]: The skill includes a reference to an external tool installation command using 'npx'.\n
- Evidence: The handoff section in SKILL.md suggests: 'npx skills add fatih-developer/fth-skills --skill '.\n
- Execution method: The 'npx' command fetches and executes code from the npm registry at runtime.\n
- Context: The resource is associated with the skill author ('fatih-developer').
Audit Metadata