source-driven-development

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behavior or security vulnerabilities were identified in the skill instructions. The skill promotes healthy development practices by requiring external documentation verification.\n- [COMMAND_EXECUTION]: The skill utilizes safe environment inspection commands such as npm ls and grep to determine dependency versions and verify configuration files.\n- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from official sources and GitHub via specialized tools. These sources are considered well-known and trusted for the purpose of technical research.\n- [PROMPT_INJECTION]: The skill possess an indirect prompt injection attack surface because it ingests data from external documentation websites.\n
  • Ingestion points: Technical documentation retrieved via WebFetch, mcp__context7__get-library-docs, and mcp__grep_app__searchGitHub.\n
  • Boundary markers: Absent.\n
  • Capability inventory: The skill can execute shell commands (Bash), edit files (Edit), and perform network requests (WebFetch).\n
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 08:14 AM
Security Audit — agent-trust-hub — source-driven-development