agentic-project-bootstrap
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by requiring agents to ingest untrusted data from the repository to scaffold instructions. Ingestion points: The agent reads existing README, docs, and AGENTS.md/CLAUDE.md files to research the repository context. Boundary markers: The skill does not provide instructions to use delimiters or ignore embedded instructions when reading these external artifacts. Capability inventory: The skill performs file writes to create documentation and generates execution instructions that command agents to run verification tests. Sanitization: No sanitization or verification of the repository's content is performed before it is used to customize the agent's core instruction set.
Audit Metadata