iblai-api-agent-history
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests conversation history and summaries from an external API, which contains untrusted user-generated content. This creates a surface for indirect prompt injection if the agent interprets text within the history as new instructions.
- Ingestion points: Data is retrieved from the
/chat-history/and/memory/API endpoints (SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to separate processed history from active commands.
- Capability inventory: The skill utilizes network operations via
curlto interact with the ibl.ai API. - Sanitization: There is no evidence of sanitization or filtering applied to the retrieved conversation data before it enters the agent's context.
Audit Metadata