brace-recon
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute find and grep commands to locate support-related files like documentation and SLAs. These are standard search operations for discovery.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface (Category 8) as it reads content from discovered local files.
- Ingestion points: Markdown, YAML, and JSON files matching support keywords found in the project directory.
- Boundary markers: None present to distinguish file content from agent instructions.
- Capability inventory: Access to tools including Bash, Read, WebFetch, and WebSearch.
- Sanitization: No sanitization of the content from the audited files is performed.
Audit Metadata