agent-first-project-bootstrap
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructional templates for project scaffolding. It actively promotes security best practices, including 'secret-scanning and repository hygiene checks' and the mechanical enforcement of architectural invariants through automated tests and CI gates.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructs agents to ingest project context from existing repository files (e.g., README.md, manifests, instructions). This represents a data ingestion surface, but since it is fundamental to the skill's primary purpose of repository bootstrapping, it is documented here neutrally.\n
- Ingestion points: Section 2 ('Inspect before modifying an existing skeleton') specifies reading the README, agent instructions, package manifests, CI/test configurations, architecture documents, and current source layout.\n
- Boundary markers: Absent; the skill does not explicitly instruct the agent to use delimiters or sanitization when processing these local files.\n
- Capability inventory: The agent is authorized to perform file system operations (create/modify) and execute shell commands for setup and validation as part of the bootstrap process.\n
- Sanitization: Absent; the skill focuses on validation of outcomes rather than input text filtering.
Audit Metadata