font-specimen
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation provides instructions for using standard command-line tools like fontTools and base64 to process font files for web embedding.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local data to generate HTML artifacts, creating a standard injection surface associated with content generation.\n
- Ingestion points: SVG glyph files and JSON metadata are read from the local _workspace directory to build the specimen pages.\n
- Boundary markers: The generation script does not implement explicit boundary markers or instructions to ignore instructions embedded within the source data.\n
- Capability inventory: The scripts/build_specimen.py script performs local file system reads and writes to generate HTML output.\n
- Sanitization: The script extracts SVG content using regular expressions but does not perform sanitization, which could allow for script injection if the source files are malicious.
Audit Metadata