Meditation Facilitation Skill
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill creates a vulnerability surface for indirect prompt injection via its knowledge consolidation protocol.
- Ingestion points: The agent is instructed to 'Review' what happened in a session to 'Record' key learnings (SKILL.md).
- Boundary markers: The instructions do not define delimiters or protective markers to separate untrusted session data from the agent's consolidation logic.
- Capability inventory: The protocol involves the agent modifying its own sensitive configuration files, including '.instructions.md' and '.prompt.md' (SKILL.md).
- Sanitization: There are no requirements for sanitizing or validating session content before it is extracted and promoted to long-term memory or operational instructions.
Audit Metadata