flomo-analysis-studio
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the local environment via shell commands. Evidence: Instructions in SKILL.md and references/query-strategy.md demonstrate the construction of commands like python3 "$SCRIPT" summarize and python3 "$SCRIPT" query to fetch data from the flomo-local-api.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection from processed data. Ingestion points: User-generated memos are ingested through the flomo-local-api as described in SKILL.md. Boundary markers: No specific delimiters or safety instructions are used to separate untrusted note content from agent instructions. Capability inventory: The agent has shell command execution privileges and is tasked with complex synthesis of untrusted text. Sanitization: No sanitization or content filtering is implemented for the notes retrieved from the local database.
Audit Metadata