hum-source-criticism
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely informational, providing structured methodologies such as the Four Tests of Source Credibility and the CRAAP test (Currency, Relevance, Authority, Accuracy, Purpose).
- [SAFE]: All external URLs referenced in
references/fact-check-tools.mdandreferences/craap-test.mdare well-known, legitimate services including established fact-checking organizations (Snopes, Reuters, AP, PolitiFact) and standard research tools (PubMed, TinEye, Google Images, ExifTool). - [SAFE]: The command-line example provided in the documentation (
exiftool suspicious_image.jpg) is a benign instructional snippet meant for manual user execution and does not represent dynamic context injection or hidden code execution. - [SAFE]: The skill does not perform any network operations, file modifications, or credential handling. It strictly defines an evaluation process and output format for the AI agent to follow when assisting users with fact-checking.
- [SAFE]: Metadata and examples are consistent with the skill's stated educational purpose, with no evidence of prompt injection or deceptive patterns.
Audit Metadata