create-readme

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches README templates from Microsoft's Azure-Samples repositories and other public GitHub repositories to provide inspiration for the structure, tone, and content of the generated documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from both the project workspace and external URLs.
  • Ingestion points: Reads content from four external raw GitHub URLs and performs a comprehensive review of all files in the project workspace.
  • Boundary markers: Absent. The instructions do not define delimiters or provide specific directives to the agent to ignore any commands that might be embedded in the ingested content.
  • Capability inventory: The skill has permissions to read from the workspace and write the resulting README.md file back to the file system.
  • Sanitization: Absent. Data fetched from external sources and project files is used directly to influence the model's output without validation or escaping mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:55 AM
Security Audit — agent-trust-hub — create-readme