ape-quiz-me

Warn

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands, specifically curl and pdftotext, to download and extract text from PDF files provided via URLs.
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch content from user-specified external URLs using WebFetch and curl.
  • [PROMPT_INJECTION]: The skill processes untrusted external data (files, URLs, and pasted text) to generate quiz content, which creates a surface for indirect prompt injection. 1. Ingestion points: Input can be provided as file paths on disk, external URLs, or raw pasted text (SKILL.md). 2. Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the processed content. 3. Capability inventory: The skill uses WebFetch, shell commands (curl, pdftotext), and file reading tools. 4. Sanitization: The skill does not implement any filtering, escaping, or validation of the external content before processing it for quiz generation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 18, 2026, 11:57 AM
Security Audit — agent-trust-hub — ape-quiz-me