The Agent Skills Directory

[SAFE]: The skill's operations are fully aligned with its stated purpose of project initialization and design context gathering. No evidence of malicious behavior, data exfiltration, or unauthorized command execution was found.
[PROMPT_INJECTION]: The skill exhibits an inherent surface area for indirect prompt injection (Category 8) because it processes untrusted content from the codebase to generate its findings. 1. Ingestion points: Step 1 involves scanning READMEs, docs, components, and other project files. 2. Boundary markers: Absent; there are no instructions to delimit or ignore instructions embedded within the scanned files. 3. Capability inventory: The agent has the capability to write to the file system (specifically .impeccable.md and .github/copilot-instructions.md). 4. Sanitization: Absent; findings are synthesized directly from scanned content. However, since this is the primary intended function of the skill, the severity is minimal.

teach-impeccable