frontier-scan
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from web search results, which creates a surface for indirect prompt injection.
- Ingestion points: WebSearch results obtained in Step 2, covering AI agent framework updates, context engineering, and marketplace security.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as untrusted data or to ignore instructions embedded within search results.
- Capability inventory: The skill can write to local HTML and Markdown files (e.g.,
llmwiki/html/overstack-vs-world-30d.html) and execute GitHub CLI commands (gh issue create,gh issue comment). - Sanitization: The instructions do not specify any validation, escaping, or filtering of search content before it is interpolated into GitHub issue bodies or local reports.
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to automate issue management. While these commands target the user's own repository and follow the stated purpose of the skill, they utilize content derived from external analysis, which represents a potential vector for command injection if input is not properly handled by the agent.
Audit Metadata