impeccable-teach-impeccable
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes project files to synthesize design guidelines, which could allow malicious instructions in those files to influence the agent's persistent configuration.
- Ingestion points: Scans local project files including README, documentation, package.json, and source code components.
- Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when reading file content.
- Capability inventory: The skill possesses file read capabilities for codebase exploration and file write capabilities for updating the 'AGENTS.md' configuration.
- Sanitization: Absent. Content inferred from the codebase is directly synthesized into the resulting markdown configuration.
Audit Metadata