academic-poster-builder
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's design and instructions are entirely consistent with its stated purpose. All capabilities, such as file searching and rendering verification, are used for legitimate academic design tasks.
- [COMMAND_EXECUTION]: The skill utilizes the
ripgrep(rg) command-line utility for discovering local assets within a research project. It also provides a Node.js utility script that leverages Playwright to automate a headless browser for checking poster layout fidelity and overflows. - [PROMPT_INJECTION]: The skill processes content from academic papers and LaTeX projects, which constitutes an indirect prompt injection surface where untrusted document content could theoretically influence the agent. This is considered a low-risk, incidental finding inherent to document processing tasks.
- Ingestion points: Academic paper sources (abstract, introduction, methods) and local project assets.
- Boundary markers: No explicit markers or "ignore" instructions are used when interpolating paper content.
- Capability inventory: Asset discovery via
rg, local file system access for reading and writing assets/posters, and HTML rendering/script execution via the provided Playwright verification tool. - Sanitization: No content validation or escaping of the ingested paper text is specified.
Audit Metadata