Skills
Navigate
skills/willbooster/exercode-problem-utils/generate-learning-content/Gen Agent Trust Hub

generate-learning-content

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the exercode-problem CLI tool using bunx to validate model answers and judge problems. This tool appears to be part of the official Exercode authoring toolchain.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external content from the repository, such as existing learning materials and repository-level instructions, which could potentially contain malicious prompts.
  • Ingestion points: Repository instructions and existing learning-content layout (referenced in Step 1).
  • Boundary markers: None identified; instructions do not specify delimiters or warnings for external data.
  • Capability inventory: The skill has the capability to execute shell commands (bunx exercode-problem).
  • Sanitization: No explicit sanitization or validation of the ingested text is mentioned before processing.
  • [EXTERNAL_DOWNLOADS]: The skill references and uses the @exercode/problem-utils package and the exercode-problem CLI tool, which are retrieved via the bunx package runner.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 09:02 AM
Security Audit — agent-trust-hub — generate-learning-content