The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown instructions and reference templates. There are no executable scripts (Python, Node.js), binaries, or shell commands included in the skill package.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided documents during its 'Requirements Review Mode' and 'Discovery Phase'. This creates a standard surface for indirect prompt injection where malicious instructions could be embedded in the text provided by a user.
Ingestion points: SKILL.md instructions for 'Existing document to review' and 'Phase 1: Discovery'.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the external content.
Capability inventory: The skill has no dangerous capabilities; it lacks access to the file system (outside of its own references), terminal, or network tools. The agent is limited to generating markdown text.
Sanitization: No explicit sanitization or filtering of user-supplied text is instructed, but the inherent lack of tool access mitigates the risk to the user's session only.

software-requirements