The Agent Skills Directory

[SAFE]: The skill functions as a text-processing utility that takes structured input (team skills, track details) and produces text output (gap analysis, social media posts). It does not request any dangerous permissions or tools.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from team descriptions and track requirements which could theoretically contain malicious instructions.
Ingestion points: current_members and target_track inputs defined in SKILL.md.
Boundary markers: Absent. The skill instructions do not specify delimiters for these inputs.
Capability inventory: None. The skill performs no subprocess calls, file writes, or network operations.
Sanitization: Absent. There is no explicit validation of the input strings. However, the lack of active capabilities makes this surface low-risk.
[EXTERNAL_DOWNLOADS]: The skill references local context files (knowledge/hackathon-winning-patterns.md and playbooks/hackathon-workflow.md). These are relative file path references to a shared internal resource folder and do not involve network requests or remote code execution.

hackathon-team-recruiter