teach-session

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of analyzing and explaining session artifacts without specific security boundaries.
  • Ingestion points: Session workstreams, problem descriptions, solutions, code artifacts, and execution logs referenced in the documentation and teaching loop.
  • Boundary markers: The instructions do not define clear delimiters or instruct the agent to ignore instructions embedded within the files being taught.
  • Capability inventory: The skill can read session files, write checklist documents to the filesystem (e.g., docs/.ai/teaching/ or /tmp/), and utilize the AskUserQuestion tool.
  • Sanitization: There is no requirement for the agent to sanitize, escape, or validate the content of the session artifacts before incorporating them into the teaching process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 03:01 AM
Security Audit — agent-trust-hub — teach-session