teach

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external sources via RESOURCES.md and user inputs to generate educational content, creating a vulnerability surface.
  • Ingestion points: External URLs and descriptions in RESOURCES.md, as well as user queries provided during the teaching sessions in the SKILL.md workspace.
  • Boundary markers: The skill uses specific Markdown templates (e.g., MISSION-FORMAT.md, LEARNING-RECORD-FORMAT.md), but lacks explicit delimiters or warnings to the model to ignore embedded instructions within resource descriptions.
  • Capability inventory: The agent is authorized to write files to the local directory (./lessons/, ./learning-records/, etc.) and is instructed to execute CLI commands to open these files.
  • Sanitization: Filenames are partially sanitized using a "dash-case" requirement, but there is no instruction to sanitize or escape the content of the generated HTML lessons, which could contain malicious scripts.
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform actions that involve the local operating system's command line.
  • Evidence: SKILL.md contains the instruction: "If possible, open the lesson file for the user by running a CLI command." This involves executing a tool (like open, xdg-open, or a browser) against a file whose content is generated from untrusted external resource data, creating a potential boundary crossing if the content is not properly handled.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 09:28 AM