github
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses the official GitHub CLI to manage repositories, pull requests, and issues.
- [EXTERNAL_DOWNLOADS]: Installation instructions reference the GitHub CLI, a well-known service, through trusted package managers.
- [PROMPT_INJECTION]: The skill ingests untrusted data from GitHub, creating a surface for indirect prompt injection.
- Ingestion points:
gh issue viewandgh pr viewcommands inSKILL.mdingest external data. - Boundary markers: No delimiters or instructions are provided to the agent to treat fetched data as untrusted.
- Capability inventory: The skill includes commands that can modify repository state (e.g., merging PRs, creating releases).
- Sanitization: Fetched data is interpolated into the agent context without sanitization.
Audit Metadata