software-development
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains purely instructional content and process guidelines for software development. No malicious code, obfuscation, or data exfiltration patterns were detected.
- [COMMAND_EXECUTION]: The skill defines a workflow for executing project-specific commands such as formatting, linting, and dependency management. These are standard development operations, and the instructions prioritize using documented project commands and seeking human approval for unknown operations.
- [INDIRECT_PROMPT_INJECTION]: The skill defines procedures for processing project files, which represents an inherent attack surface for indirect prompt injection.
- Ingestion points: Project source code, manifest files (e.g.,
package.json), and contributor documentation (e.g.,README.md) read during development tasks. - Boundary markers: None explicitly defined within the skill instructions; relies on platform-level delimiters.
- Capability inventory: File writing, execution of formatting/linting tools, and dependency management via
npm. - Sanitization: Mitigated by mandatory manual verification of all outputs and requiring human approval before adopting new or undocumented project commands.
Audit Metadata