fingerprint-get-started
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads project manifest files (e.g., package.json, requirements.txt) to identify dependencies and automatically select sub-skills for the setup process.\n
- Ingestion points: Manifest files at the root and up to two levels deep in the project structure are read by the agent to determine the tech stack (detected frameworks mapping).\n
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be maliciously embedded within these manifest files.\n
- Capability inventory: Based on findings in the manifests, the skill performs automated skill delegation, code generation, and provides instructions for package installation.\n
- Sanitization: The skill does not include steps to sanitize or validate the content of the manifest files before using that information to decide the orchestration path.
Audit Metadata