local-conversation-history
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the retrieval and processing of historical conversation data, which is a potential vector for indirect prompt injection if those logs contain malicious instructions.
- Ingestion points: The skill searches through 'session bodies' and historical 'metadata' based on user keywords (defined in SKILL.md).
- Boundary markers: The instructions lack specific guidance on using delimiters or wrappers to prevent the agent from executing instructions found within the retrieved history.
- Capability inventory: The router directs the agent to tools capable of reading the file system and performing task continuation (e.g., daymade-claude-code:continue-claude-code-work).
- Sanitization: The instructions do not mandate sanitization or escaping of retrieved conversation content.
Audit Metadata