flomo-analysis-studio

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with a local API via shell commands (e.g., python3 "$SCRIPT" summarize) to fetch user data for analysis. This is documented as the standard data access method for the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-generated content from flomo notes, which creates an attack surface for indirect prompt injection. 1. Ingestion points: Output from flomo-local-api summarize and query commands. 2. Boundary markers: Absent; no specific instructions to use delimiters or ignore embedded instructions. 3. Capability inventory: Ability to execute shell commands via the local API and perform interpretive text synthesis. 4. Sanitization: Absent; no mention of content filtering or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 02:09 PM
Security Audit — agent-trust-hub — flomo-analysis-studio