express-insight

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill. It consists entirely of natural language instructions.
  • [NO_CODE]: The skill is composed strictly of documentation and metadata with no executable scripts or binary files.
  • [SAFE]: Indirect Prompt Injection Surface: The skill processes user-provided insights and uses Read/Write tools, but lacks dangerous execution sinks. 1. Ingestion points: 'insight' and 'audience' inputs in SKILL.md. 2. Boundary markers: None present. 3. Capability inventory: Read and Write tools defined in SKILL.md frontmatter. 4. Sanitization: No sanitization or validation of input data is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 07:14 AM