create-readme
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch external Markdown documents from remote GitHub repositories (
Azure-Samplesandsinedied) to use as structural templates. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting external data without boundary markers.
- Ingestion points: Remote URLs specified in
SKILL.mdtask instructions. - Boundary markers: Absent; there are no explicit delimiters or instructions guiding the agent to disregard instructions within the source files.
- Capability inventory: Limited to workspace text file creation (
README.md). No arbitrary command execution, dynamic evaluations, or sensitive data accesses are present. - Sanitization: Absent.
Audit Metadata