specialized-developer-advocate
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from untrusted external sources such as GitHub issues, Stack Overflow questions, and community chat platforms (Discord/Slack), which represents an attack surface for indirect prompt injection. This is a standard risk for the role of developer advocacy. \n- Ingestion points: GitHub issues, Stack Overflow, Discord, Slack, developer surveys. \n- Boundary markers: Not explicitly defined in the instructions. \n- Capability inventory: Technical content creation and product feedback; script execution via a local runner (run.sh). \n- Sanitization: Not explicitly defined. \n- [COMMAND_EXECUTION]: Documentation templates reference shell commands such as npm and npx for instructional purposes. These are used within educational content and are not executed by the agent as part of its internal logic. \n- [EXTERNAL_DOWNLOADS]: The skill references external platforms like GitHub and Vercel for hosting sample code and deployment examples, which is routine for the intended advocacy purpose.
Audit Metadata