The Agent Skills Directory

[NO_CODE]: The skill is entirely descriptive, consisting of markdown instructions and YAML metadata. It does not include any scripts, binaries, or package dependencies.
[SAFE]: No malicious patterns, such as data exfiltration or credential harvesting, were identified. The skill's scope is strictly limited to providing design advice and referencing other design-related skills.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze an external codebase to identify design intensity sources. This establishes a data ingestion surface for potentially untrusted content. However, the risk is negligible as the skill lacks any tools, execution environments, or network sinks that could be exploited. 1. Ingestion points: User-provided codebase (referenced in SKILL.md under 'Assess Current State'). 2. Boundary markers: Absent. 3. Capability inventory: None (no tools or script execution defined in the frontmatter or body). 4. Sanitization: Absent.

quieter