suggest-awesome-github-copilot-skills
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches skill definitions and associated assets from the official GitHub 'awesome-copilot' repository.
- [COMMAND_EXECUTION]: Utilizes terminal commands such as
curlto retrieve skill content and bundled assets fromraw.githubusercontent.com. - [DATA_EXFILTRATION]: Performs local scans of the
.github/skills/directory to build a capability inventory, ensuring no duplicates or outdated versions exist; no sensitive data is transmitted outside of the trusted organization domain. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from a remote repository and local files.
- Ingestion points: Processes content from
README.skills.mdand remoteSKILL.mdfiles. - Boundary markers: No explicit delimiters are defined to separate remote instructions from system prompts.
- Capability inventory: Possesses file write access and the ability to execute terminal commands via
#runInTerminal. - Sanitization: No explicit sanitization or validation logic is defined for the downloaded markdown content before processing.
Audit Metadata