posterskill-academic-posters

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill clones a core repository from GitHub (ethanweber/posterskill) and fetches paper sources from Overleaf.
  • [COMMAND_EXECUTION]: Uses shell commands to clone repositories and manage the local environment.
  • [EXTERNAL_DOWNLOADS]: Automatically downloads institutional logos from project websites using Playwright during the generation process.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from LaTeX files and external URLs which could serve as an attack surface for indirect prompt injection.
  • Ingestion points: LaTeX source files in 'overleaf/' directory, reference PDFs, and conference/project URLs.
  • Boundary markers: No specific delimiters or instruction-ignore markers are present in the documentation.
  • Capability inventory: Shell command execution (git), file system modifications, and network operations via Playwright.
  • Sanitization: No mention of input sanitization or validation of the ingested LaTeX or PDF content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 08:19 AM