im-adapter
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its group memory feature, which involves reading from and writing to files containing historical chat data.
- Ingestion points: The agent ingests untrusted data from the MemoryFile (e.g., memory/groups/slack-team.md) and user-attributed messages within group conversations.
- Boundary markers: Absent. The instructions do not provide methods for the agent to distinguish between its own logic and instructions that may be embedded within the chat history or memory files.
- Capability inventory: The skill requires the ability to read and write files to manage project context and persistent memory.
- Sanitization: Absent. No procedures are defined for sanitizing, escaping, or validating the content stored in or retrieved from the memory system.
Audit Metadata