fetch-abstract-to-kb
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script executes the
openclawCLI tool using thesubprocessmodule to manage browser sessions and extract page content. Arguments are passed as a list, preventing shell injection vulnerabilities. - [EXTERNAL_DOWNLOADS]: The skill navigates to external URLs (specifically
doi.organd its redirects) via the OpenClaw browser to retrieve metadata for scholarly articles. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted content from the web and writes it to a database.
- Ingestion points: Data is fetched from external websites through the
extract_abstract_from_doifunction inscripts/fetch_abstract_to_kb.py. - Boundary markers: No delimiters or instructions are used to isolate the fetched text from other agent inputs.
- Capability inventory: The skill possesses the ability to execute CLI commands and perform database write operations.
- Sanitization: The script normalizes whitespace but does not filter for potential instructions or prompt injection patterns in the retrieved text.
Audit Metadata