crw-research
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill interacts with an external API at
api.fastcrw.com. This domain is associated with the skill's homepage and author. It correctly instructs the agent to use an environment variable (FASTCRW_API_KEY) for authentication rather than hardcoding credentials. - [COMMAND_EXECUTION]: The skill uses
curlandjqvia theBashtool to perform API requests and parse JSON results. These operations are limited to the intended purpose of retrieving research paper metadata. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API responses (arXiv paper metadata). While this represents a theoretical attack surface common to all search-based skills, the risk is minimal as the ingested data consists of structured academic records, and the skill performs no high-risk operations with the parsed content.
Audit Metadata