axiom-audit-camera
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 involves scanning and reading untrusted external data in the form of Swift source code, which could contain adversarial instructions hidden in comments or strings meant to influence the agent's analysis results.\n
- Ingestion points: The skill instructions direct the agent to use
GlobandReadtools to scan project directories and representative files (e.g.,**/*.swift).\n - Boundary markers: The instructions lack explicit boundary markers or directives to treat the content of the files as data only and to ignore any embedded instructions.\n
- Capability inventory: The agent leverages
Glob,Grep, andReadtools to perform code analysis and generates complex reports and reliability health scores.\n - Sanitization: No sanitization, validation, or escaping of the code content is performed before it is analyzed by the agent.
Audit Metadata