episodic-memory
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates context retrieval from past conversations via internal search tools. While this involves accessing historical project data, it is restricted to the agent's internal memory systems and no exfiltration patterns were found.
- [PROMPT_INJECTION]: No direct prompt injection or safety bypass instructions are present. The skill has an indirect prompt injection surface because it processes historical data. 1. Ingestion points: episodic_memory_search in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: episodic_memory_search, episodic_memory_show. 4. Sanitization: Absent.
- [EXTERNAL_DOWNLOADS]: No external package dependencies or remote code execution patterns were detected.
- [COMMAND_EXECUTION]: No unauthorized system commands, shell scripts, or privilege escalation attempts are included in the skill.
Audit Metadata