axiom-audit-database-schema
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted project files using
Glob,Grep, andReadtools to identify database schema issues. It lacks specific instructions for the agent to distinguish between its own auditing instructions and potentially malicious instructions embedded within the audited source code (e.g., in code comments or string literals). - Ingestion points: Processes the user's project files through
Globpatterns (e.g.,**/*.swift) andGrepsearches for database keywords. - Boundary markers: The skill does not define specific delimiters or "ignore embedded instructions" warnings for the content it reads.
- Capability inventory: The skill utilizes
Glob,Grep, andReadtools for architecture mapping and anti-pattern detection. - Sanitization: The instructions do not specify any validation or sanitization procedures for the external content before analysis.
Audit Metadata