touch-feature
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands such as
grep,find, andlsto identify the technology stack, framework, and architectural patterns within the target project's files.- [PROMPT_INJECTION]: The skill is exposed to indirect prompt injection by reading and processing project files that may contain untrusted content. - Ingestion points: Project configuration files (package.json, pubspec.yaml, build.gradle) and source code files (.swift, .kt, .ts, .tsx, .dart) processed in SKILL.md.
- Boundary markers: No specific delimiters are employed to isolate external data from instructions.
- Capability inventory: The skill possesses the ability to execute shell commands and modify files via the Bash, Write, and Edit tools.
- Sanitization: Content read from the project is not sanitized or filtered before being incorporated into the agent's context.
Audit Metadata