teach-me

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data from the project session, creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: The instructions in SKILL.md direct the agent to "Identify the session's work (changes, decisions, code)" and "Explore the project as needed."
  • Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to disregard instructions found within the project files it is analyzing.
  • Capability inventory: While disable-model-invocation: true is set, the skill instructions reference "Show them code or have them use the debugger," indicating the agent interacts with the development environment and potentially powerful tools.
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the project files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 10:11 AM