qinyan-citation
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local bash script
scripts/search.shwhich utilizescurlandpython3to interact with an external API. This execution is scoped to the skill's primary function of retrieving academic metadata. - [EXTERNAL_DOWNLOADS]: The search script performs network requests to
api.qinyanai.com. This is a vendor-owned domain (qinyan-ai) used for fetching legitimate academic data. - [PROMPT_INJECTION]: The skill processes external data retrieved from academic databases. While this constitutes an indirect prompt injection surface (where malicious instructions could be embedded in paper titles), the skill provides a strict output schema and lacks high-privilege capabilities that could be abused by such an injection.
- [CREDENTIALS_UNSAFE]: The skill correctly instructs users to manage sensitive API keys via environment variables (
QINYAN_API_KEY), which is a recommended security practice for secret management.
Audit Metadata