ship-learn-next

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from user-provided files and uses that information to generate structured output.\n
  • Ingestion points: The agent is instructed in SKILL.md to use the Read tool on user-specified files.\n
  • Boundary markers: No explicit delimiters or instructions are provided to isolate the external content or to instruct the agent to ignore any embedded commands within the input files.\n
  • Capability inventory: The skill uses Read and Write tools to interact with the file system, creating a potential path for data-driven influence on file operations.\n
  • Sanitization: There are no instructions to sanitize or validate the content extracted from the files before using it to generate quest titles, success criteria, or final filenames.\n
  • Mitigation: Include instructions to wrap external content in delimiters and explicitly ignore embedded instructions. Additionally, the agent should be instructed to validate and sanitize any strings used for file names or command arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 12:08 PM
Security Audit — agent-trust-hub — ship-learn-next