paddleocr-doc-parsing
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the paddleocr CLI to perform complex document parsing tasks including layout analysis and table extraction.
- [EXTERNAL_DOWNLOADS]: The skill allows the agent to download and process files from remote URLs using the --file_url argument.
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from external documents and provides it to the agent, creating a surface where malicious instructions in the source document could influence agent behavior.
- Ingestion points: File content from --file_url and --file_path in SKILL.md.
- Boundary markers: None.
- Capability inventory: Shell command execution (paddleocr) in SKILL.md.
- Sanitization: No sanitization or validation of the extracted text is performed before returning it to the agent context.
Audit Metadata