api-designer

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's instructions and logic are consistent with its stated purpose of assisting in API design. No malicious patterns, obfuscation, or unauthorized exfiltration attempts were identified.
  • [COMMAND_EXECUTION]: The skill uses local Python scripts (scripts/generate_api.py and scripts/validate_api.py) to automate documentation tasks. These scripts rely on standard Python libraries (pathlib, argparse) for file operations and do not execute arbitrary shell commands or remote payloads.
  • [EXTERNAL_DOWNLOADS]: The skill references external resources from well-known and trusted sources, including official documentation for GraphQL, REST API tutorials, and Microsoft's API guidelines on GitHub. These references are used for informational purposes.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it is designed to read and process API specifications.
  • Ingestion points: scripts/validate_api.py (reads input files), SKILL.md (describes reviewing existing designs).
  • Boundary markers: Absent.
  • Capability inventory: Bash (execution of local scripts), Read, Write, WebFetch.
  • Sanitization: None identified in the provided scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 02:05 AM