pravidhi-yc-oss
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The script
scripts/yc_client.pyfetches company data fromhttps://yc-oss.github.io/api, which is a public GitHub Pages site. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through external data ingestion.
- Ingestion points: In
scripts/yc_client.py, data is fetched from a remote GitHub Pages API. - Boundary markers: There are no boundary markers or specific instructions to the agent to disregard potential commands found within the fetched company names or descriptions.
- Capability inventory: The script performs network requests and formats data for agent consumption.
- Sanitization: The script does not sanitize the content for potential prompt injection strings, although it does truncate descriptions to 100 characters.
Audit Metadata