antinet-four-color-cards

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a Python script (scripts/run_four_color_cards.py) to orchestrate document processing and card generation. It writes analysis results to a local output directory (examples/snse_survey/skill_outputs).
  • [PROMPT_INJECTION]: The skill processes external markdown documents and user intent, creating a surface for indirect prompt injection.
  • Ingestion points: Ingests markdown data and user intent strings as inputs to the card generation process.
  • Boundary markers: Absent; there are no explicit delimiters or system instructions provided to differentiate document content from control instructions.
  • Capability inventory: The skill has the capability to write files locally and invoke LLM models to generate text.
  • Sanitization: Absent; no evidence of input sanitization or validation of the provided markdown content was found in the scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 06:40 AM
Security Audit — agent-trust-hub — antinet-four-color-cards