The Agent Skills Directory

[SAFE]: The skill's primary content is high-quality documentation and structured templates for UX research. A thorough audit of all instructions and reference files revealed no evidence of prompt injection, persistence mechanisms, or unauthorized data access.
[EXTERNAL_DOWNLOADS]: The skill recommends installing a related quality-auditor skill using the 'pnpm dlx skills' utility. This command targets the official 'oakoss' repository, which matches the skill author's verified identity, and represents standard modular skill management rather than a security risk.
[INDIRECT_PROMPT_INJECTION]: The skill provides templates for analyzing user quotes and test observations, which constitutes a vulnerability surface for processing untrusted external data. * Ingestion points: The skill instructs the agent to analyze raw participant feedback and session notes as documented in references/reporting.md. * Boundary markers: The provided templates do not explicitly implement boundary markers or instructions to ignore embedded commands within qualitative data. * Capability inventory: The skill does not define any dangerous capabilities such as direct network operations, system-level file writes, or subprocess execution. * Sanitization: No specific sanitization or filtering logic is recommended for the qualitative data inputs.

usability-tester