dev-new-tool
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from web searches and API documentation during the research phase, creating a vulnerability surface where instructions embedded in external content could influence the agent's actions. * Ingestion points: Web search results and external API documentation (SKILL.md, Phase 1). * Boundary markers: User approval checkpoints are included between each phase of the workflow. * Capability inventory: The skill can write files and execute shell commands for project setup and verification. * Sanitization: No explicit sanitization or filtering of external content is described.
- [COMMAND_EXECUTION]: The skill executes various system commands to initialize projects and verify code quality. * Evidence: The workflow involves running
go mod init,npm init,git commit,eslint, andgo vet(SKILL.md, Phase 4 and Phase 5).
Audit Metadata