brief
Warn
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation in references/visual-explainer.md instructs users to install an external skill by running git clone https://github.com/nicobailon/visual-explainer. This repository is not verified and originates from an author different from the skill creator, posing a potential risk of downloading and executing untrusted code.
- [PROMPT_INJECTION]: The skill processes content from plan files and research artifacts that may contain data from untrusted sources. This surface could be exploited via indirect prompt injection to influence the agent behavior during the briefing process. * Ingestion points: Reads plan and support files from .claude/plans/ (e.g., plan.md, scratchpad.md). * Boundary markers: The skill rephrases content into templates but lacks explicit delimiters or instructions to ignore embedded commands. * Capability inventory: Read access to the filesystem via Glob and interactive user communication. * Sanitization: No input validation or content filtering is implemented for the plan data.
Audit Metadata