The Agent Skills Directory

[PROMPT_INJECTION] (LOW): This skill is vulnerable to indirect prompt injection (Category 8) because it ingests external content for processing. Mandatory Evidence Chain: (1) Ingestion points: The skill explicitly reads user-provided 'Theory' and 'Findings' sections as specified in phases/phase0-intake.md. (2) Boundary markers: Absent; there are no instructions to delimit or ignore instructions within the user-provided text. (3) Capability inventory: The skill utilizes the Task tool for text generation and internal orchestration but has no file system write, network access, or command execution capabilities. (4) Sanitization: None identified. The risk is limited to the agent's internal reasoning and generated output.
[NO_CODE] (INFO): The skill consists entirely of instructional Markdown files. No Python, Node.js, or shell scripts were found, and no remote code execution patterns were detected.

interview-bookends