skills/ilteoood/harness/create-readme/Gen Agent Trust Hub

create-readme

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references README files from the Azure-Samples organization and community repositories on GitHub to serve as structural and stylistic templates for documentation generation. These sources are considered well-known and consistent with the intended task.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external URLs, which creates a surface for indirect prompt injection. Ingestion points: SKILL.md (via external URL references). Boundary markers: Absent. Capability inventory: File system write (creating README.md). Sanitization: None specified. While this presents an ingestion surface, the risk is minimal given the reputable sources and the restricted scope of documentation creation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 02:45 PM
Security Audit — agent-trust-hub — create-readme