glmocr
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'glmocr' package from the Python Package Index (PyPI), which is a standard package registry.
- [COMMAND_EXECUTION]: The skill invokes the 'glmocr' command-line interface to perform document parsing, which involves local file system access and process execution.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Malicious instructions embedded within images or PDFs could be extracted by the OCR process and subsequently interpreted by the agent.
- Ingestion points: Document files (images, PDFs) provided as paths to the 'glmocr.parse' function in SKILL.md.
- Boundary markers: None identified; the extracted text is passed directly to the agent in Markdown or JSON format.
- Capability inventory: The skill has the ability to write files to the local system (result.save) and execute CLI commands.
- Sanitization: No specific sanitization or filtering of the OCR output is documented before it is returned to the agent context.
Audit Metadata