Skills
Navigate
skills/qinyan-ai/qinyan-academic-skills/qinyan-paper-search/Gen Agent Trust Hub

qinyan-paper-search

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to api.qinyanai.com to retrieve search results from academic databases including Google Scholar, Wanfang, PubMed, and ArXiv.
  • [COMMAND_EXECUTION]: The skill utilizes a local shell script, scripts/search.sh, to execute curl commands. The script includes a validation step using python3 to ensure that user-provided search parameters are in a valid JSON format before transmission.
  • [PROMPT_INJECTION]: The skill has a data ingestion surface for user-provided queries.
  • Ingestion points: User-supplied search queries are passed as the query field in JSON payloads within SKILL.md and scripts/search.sh.
  • Boundary markers: No explicit boundary markers or instruction-ignore delimiters are present in the prompt instructions.
  • Capability inventory: The skill is capable of performing network requests via curl to the vendor's API endpoint.
  • Sanitization: The scripts/search.sh script validates the structure of the JSON payload using python3 -c, though it does not perform semantic sanitization of the query content itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 07:59 PM