teach-impeccable
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local project environment to generate persistent instructions.
- Ingestion points: The skill reads several files in the project root, including
README.md,package.json, documentation, components, and CSS files. - Boundary markers: No specific delimiters or safety instructions are defined to distinguish between data and instructions when reading project files.
- Capability inventory: The skill uses file-writing capabilities to create or append to
CLAUDE.mdin the project root. This file typically contains persistent instructions that guide the agent's behavior in subsequent sessions. - Sanitization: The skill lacks explicit sanitization or filtering of the content gathered from the codebase before synthesizing it into the
Design Contextwritten to the configuration file.
Audit Metadata