onboard
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository content to generate summaries, which creates an attack surface for indirect prompt injection. 1. Ingestion points: The skill reads project-level configuration files (CLAUDE.md, AGENTS.md), agent definitions (.claude/agents/), git history, and various source code directories. 2. Boundary markers: Absent. No specific delimiters or instructions are provided to the agent to distinguish potentially untrusted file content from system instructions. 3. Capability inventory: The skill utilizes Read, Glob, Grep, and Write tools to analyze the repository and output markdown documentation. 4. Sanitization: Absent. Content from the file system is interpreted and summarized by the model without escaping or filtering.
- [SAFE]: The skill's primary function is to facilitate project documentation and onboarding workflows within a local context. It does not perform network operations, execute remote code, or require elevated privileges.
Audit Metadata