The Agent Skills Directory

[SAFE]: The skill is entirely comprised of markdown documentation and reference files. It does not include any executable scripts, binaries, or automated command-line instructions.- [SAFE]: No evidence of obfuscation, multi-layer encoding, or hidden content was found. All external domain references are to well-known technology organizations, academic entities, and reputable research sources.- [NO_CODE]: The skill does not ship with any code or dependencies, eliminating risks related to remote code execution or malicious package installation.- [PROMPT_INJECTION]: The skill provides an ingestion surface for untrusted external data such as project specifications and GitHub issues. However, because the skill does not utilize high-privilege tools or network access, the risk of indirect prompt injection is mitigated. Evidence chain: 1. Ingestion points: User-provided task descriptions, specs, and GitHub issues (SKILL.md). 2. Boundary markers: No explicit delimiters or ignore-instructions warnings are defined. 3. Capability inventory: Generates markdown-based routing plans; no shell, execution, or network tools are invoked. 4. Sanitization: No input validation or sanitization routines are specified for ingested text.

maptasks