cli-anything-qgis

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from QGIS projects and vector layers, which could serve as a vector for indirect prompt injection if the data contains malicious instructions.
  • Ingestion points: The skill reads external files via 'project open', 'feature list', and 'process run' commands.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate data from commands.
  • Capability inventory: The skill can write to the filesystem through 'project save' and 'export' commands, and execute QGIS-specific logic via 'process run' (interacting with qgis_process).
  • Sanitization: No sanitization or validation of input data content is described.
  • [DYNAMIC_EXECUTION]: The skill is designed to execute QGIS processing algorithms and run an interactive REPL. These capabilities are consistent with the tool's primary purpose as a GIS automation utility and use the local QGIS environment.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill interacts with the local filesystem to save project files and export results. There are no patterns indicating unauthorized data exfiltration to external domains or hardcoded credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:02 PM
Security Audit — agent-trust-hub — cli-anything-qgis