axiom-audit-iap
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze untrusted source code from a user's environment, which creates a potential surface for indirect prompt injection. If a scanned file contains malicious instructions within comments or string literals, it could theoretically attempt to influence the agent's behavior.
- Ingestion points: The skill uses
Glob,Grep, andReadtools to examine the contents of.swiftand.storekitfiles throughout the project directory (Phase 1 and Phase 2). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when the agent processes code snippets from the scanned files.
- Capability inventory: The skill is scoped to file system analysis using
Glob,Grep, andRead. No network operations, file-write capabilities, or dynamic execution patterns were detected. - Sanitization: The skill lacks instructions for the agent to sanitize, escape, or validate the content of the project files it reads before performing its audit analysis.
Audit Metadata