geo-structured-writer

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external content to reformat it into structured layouts, creating an indirect prompt injection surface.
  • Ingestion points: The skill ingests data via the --input flag in scripts/structure_content.py and through the unstructured text processed by the agent as instructed in SKILL.md.
  • Boundary markers: No delimiters or specific 'ignore embedded instructions' warnings are used to wrap the untrusted content.
  • Capability inventory: The skill contains a script with file read and write capabilities (open with 'r' and 'w' modes).
  • Sanitization: The skill does not perform sanitization, escaping, or validation of the input content before processing it.
  • [COMMAND_EXECUTION]: The skill provides a local Python script for content processing that interacts with the file system.
  • Evidence: scripts/structure_content.py uses argparse to accept file paths and performs direct file read/write operations based on those arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 02:33 AM