impeccable-teach-impeccable
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from potentially untrusted files within the codebase.
- Ingestion points: The agent is instructed to scan READMEs, package.json, source code components, and style guides in the project directory (SKILL.md).
- Boundary markers: No delimiters or instructions are used to distinguish between data and instructions in the processed files.
- Capability inventory: The skill has the ability to read project files and write to the AGENTS.md file. It does not perform network operations or execute arbitrary commands.
- Sanitization: There is no logic to sanitize or filter out potential instructions hidden in the codebase files.
Audit Metadata