daily-coding
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains no malicious code, hidden commands, or persistence mechanisms. It is purely instructional and aimed at improving code quality.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and modify external source code files, which is a potential surface for indirect prompt injection. The skill includes specific safeguards to address this risk. 1. Ingestion points: Target files accessed via the Read tool as described in the Core Checklist. 2. Boundary markers: Instructions to read and understand existing code logic and design intent before modification. 3. Capability inventory: Use of Edit and Write tools to modify files. 4. Sanitization: Explicit instructions to perform security checks for command injection, XSS, and SQL injection, and to validate/escape user input.
Audit Metadata