reference-seek

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the gh (GitHub CLI) to verify authentication status and perform API searches for repositories matching user-defined topics.
  • [EXTERNAL_DOWNLOADS]: Source code is retrieved from raw.githubusercontent.com using curl. This is performed to provide the user with real-world implementation examples and follows standard developer workflows using a well-known code hosting service.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted code from external GitHub repositories to provide implementation insights.
  • Ingestion points: External source code is fetched via curl from GitHub in Step 3-3.
  • Boundary markers: The fetched content is intended to be presented within markdown code blocks in the final output.
  • Capability inventory: The skill uses gh api, curl, WebSearch, and a subagent Task(Explore) for local file access.
  • Sanitization: No specific sanitization or filtering of the fetched code is described before it is processed by the agent's logic for extraction.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 11:01 AM