axiom-audit-core-data
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external project files using tools like Glob, Grep, and Read. While intended for auditing, these ingestion points represent an attack surface where maliciously crafted comments or code in the analyzed project could attempt to influence the agent's behavior during the reasoning phases.
- Ingestion points: User-provided source code files (e.g., .swift, .xcdatamodeld) analyzed in Phases 1 through 3.
- Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the files being read.
- Capability inventory: The agent has the ability to discover the file structure (Glob), search file contents (Grep), and read file data (Read).
- Sanitization: There are no instructions for sanitizing or escaping the content read from external files before the agent processes and reasons about the data.
Audit Metadata