bible-fact-check
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
fetch_url.py,detect_desktop.py) viauv runand uses shell commands likegrep,awk, andsedto extract data from reference files. - [EXTERNAL_DOWNLOADS]: External content is retrieved from user-provided URLs using a headless browser (Chromium) managed by
patchrightto bypass website access restrictions. - [PROMPT_INJECTION]: Indirect Prompt Injection Risk: The skill processes data from external URLs and arbitrary local files which could contain malicious instructions designed to influence agent behavior.
- Ingestion points: External URLs, user-provided file paths, and pasted text.
- Boundary markers: Absent; the skill does not wrap ingested content in delimiters or provide instructions to ignore embedded commands.
- Capability inventory: Includes file system read access and the ability to execute subprocesses via
uv run. - Sanitization: No evidence of input validation or escaping for the ingested content.
Audit Metadata