suggest-awesome-github-copilot-prompts

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches prompt lists and file content from github.com and raw.githubusercontent.com specifically targeting the github/awesome-copilot repository.
  • [COMMAND_EXECUTION]: Utilizes curl through a terminal tool to download assets directly into the local .github/prompts/ directory upon user request.
  • [PROMPT_INJECTION]: Ingests external markdown content and local repository files for analysis. The process lacks explicit delimiters or sanitization for the ingested data, presenting a surface for potential indirect prompt injection from the remote source or local files.
  • [DATA_EXFILTRATION]: Accesses chat history and repository metadata to provide relevant suggestions. Analysis shows that network requests are limited to the vendor's repository domains, with no evidence of sensitive data being transmitted to unauthorized endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 05:26 AM