skills/google/mantis/mantis-report/Gen Agent Trust Hub

mantis-report

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • Local Workspace Operations: The skill is restricted to reading and writing files within the workspace/ directory, which is appropriate for its intended reporting function. It does not attempt to access sensitive system paths or credentials.
  • Indirect Prompt Injection Surface: The skill processes external data from JSON files located in workspace/findings/. While this represents a potential surface for indirect prompt injection, the risk is low as the skill's primary task is formatting and summarization.
  • Ingestion points: Reads JSON files from the workspace/findings/ directory.
  • Boundary markers: None explicitly defined in the instructions to separate data from instructions.
  • Capability inventory: The skill performs file read and write operations within the designated workspace.
  • Sanitization: The instructions do not specify sanitization or escaping of the finding content before it is interpolated into the final report template.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:20 PM
Security Audit — agent-trust-hub — mantis-report