desktop-develop
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of external data.
- Ingestion points: The agent is instructed to read application logs (e.g.,
~/Library/Logs/@craft-agent/electron/main.log) and capture UI accessibility snapshots via the Chrome DevTools MCP. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore embedded instructions within the logs or UI data.
- Capability inventory: The skill allows the agent to execute local shell commands via
bun runand perform filesystem writes to.qwen/investigations/or/tmp. - Sanitization: There is no evidence of log sanitization or UI content filtering before the data is processed by the agent.
- [COMMAND_EXECUTION]: The skill facilitates the execution of local development and build scripts.
- The instructions direct the agent to run various
buncommands (e.g.,bun run electron:dev,bun test,bun run typecheck) within thepackages/desktopdirectory. - While these are standard development tasks, they involve the execution of local project code and configuration files.
Audit Metadata