flomo-insight
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the local system by executing shell commands. It instructs the agent to use
python3 "$SCRIPT"with specific flags to retrieve and summarize user data from flomo, which is the intended mechanism for note analysis.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted user-generated content from flomo memos.\n - Ingestion points: Data enters the agent's context through the output of the
flomo-local-apitool, as specified inreferences/query-strategy.md.\n - Boundary markers: The instructions do not define clear delimiters or use protective framing to separate analyzed memo content from the agent's core instructions.\n
- Capability inventory: The agent has the ability to execute shell commands to interact with the local data layer.\n
- Sanitization: There is no mention of content sanitization or filtering applied to the memos before they are interpreted by the agent.
Audit Metadata