security-scan
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the @fusengine/harness command-line utility via bun to perform the security analysis on the specified directory.
- [DYNAMIC_EXECUTION]: The scanner tool is loaded and executed from a file path determined at runtime relative to the plugin root.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code from the user's project directory.
- Ingestion points: Files within the target directory scanned for vulnerability patterns as described in SKILL.md and references/scan-patterns.md.
- Boundary markers: The skill does not explicitly define markers to prevent the agent from interpreting instructions embedded within the scanned code.
- Capability inventory: Executes a shell command using bun, reads file content, and communicates findings to a subagent (fuse-ai-pilot:sniper).
- Sanitization: There is no documented sanitization process for the code snippets extracted during the scan.
Audit Metadata