pr-artifact-explorer
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external websites and GitHub resources, making it a target for instructions embedded in data to influence the agent's behavior.
- Ingestion points: GitHub Pull Requests, Issues, Actions artifacts, and arbitrary web URLs accessed via the open_target and navigate_browser actions in SKILL.md.
- Boundary markers: The documentation does not provide instructions for using delimiters to isolate untrusted external content from the agent's primary system prompt.
- Capability inventory: The agent has access to web navigation tools, screenshot capabilities (file-write), and file inspection tools for zip-based artifacts.
- Sanitization: The skill provides defensive instructions, including a strict prohibition on executing code found within artifacts and the requirement to honor security headers like Content Security Policy (CSP).
Audit Metadata