axiom-audit-memory

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs static analysis of Swift source code using grep and glob patterns to identify resource management anti-patterns. This is a legitimate development task with no malicious intent.\n- [COMMAND_EXECUTION]: The skill utilizes the xcsym tool to process crash reports. This command-line operation is a functional requirement for the memory auditing workflow and does not involve unsafe interpolation of untrusted input.\n- [PROMPT_INJECTION]: The skill ingests untrusted data in the form of Swift source files and crash artifacts. While this presents a surface for indirect prompt injection, the skill's capabilities are restricted to static analysis and reporting, with no network access or destructive filesystem operations.\n
  • Ingestion points: Reads project Swift files and user-provided crash logs (.ips, .crash).\n
  • Boundary markers: No explicit delimiters are used to separate ingested code content from the agent's instructions.\n
  • Capability inventory: The skill uses grep, glob, and xcsym. It does not have access to the network or file-write operations.\n
  • Sanitization: Content is analyzed by the model without additional escaping or sanitization layers.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 12:45 AM
Security Audit — agent-trust-hub — axiom-audit-memory