teach-impeccable
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing untrusted codebase data into persistent instructions.
- Ingestion points: The agent reads content from the README, documentation,
package.json, and existing components during codebase exploration. - Boundary markers: No delimiters or explicit instructions are provided to the agent to prevent it from obeying instructions potentially embedded within those files.
- Capability inventory: The skill is capable of writing and updating project files such as
.impeccable.mdand.github/copilot-instructions.md. - Sanitization: No sanitization or validation of the discovered content is performed before it is synthesized into the persistent design context.
Audit Metadata