convert

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues or malicious patterns were identified in the skill. The logic follows a standard document transformation workflow.\n- [PROMPT_INJECTION]: Evaluated the risk surface for indirect prompt injection from processed specification files:\n
  • Ingestion points: Reads external data from source files provided in arguments via the Read tool.\n
  • Boundary markers: None explicitly mentioned in the skill instructions to isolate file content from conversion instructions.\n
  • Capability inventory: The skill has permission to use Read, Glob, Grep, Write, Edit, Skill, and Task tools, enabling file modifications and invocation of other agents.\n
  • Sanitization: No explicit sanitization or filtering of the file content for malicious prompt instructions is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 07:48 AM
Security Audit — agent-trust-hub — convert