The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes user-supplied data (the {topic} variable) and interpolates it directly into the instruction prompts for six different AI personas (Scope, Logic, Mythos, Bridge, Meta, and Pattern AI).
Ingestion points: The {topic} variable is used across all role-specific prompts defined in SKILL.md.
Boundary markers: The skill attempts to delimit the input using double quotes (e.g., TOPIC: "{topic}"), which provides minimal protection against adversarial input designed to break out of the string literal and hijack the sub-agent's instructions.
Capability inventory: The skill utilizes the Agent tool to spawn sub-agents and performs filesystem operations to write multiple Markdown files and an HTML report.
Sanitization: There is no evidence of input validation, escaping, or filtering for the user-provided topic before it is passed to downstream sub-agents or written to local files.
[EXTERNAL_DOWNLOADS]: The skill's documentation describes generating an optional HTML visualization (inquiry-report.html) that may include external libraries.
Evidence: The skill mentions the use of Chart.js for rendering an "epistemic signature" radar chart in the visual report.
Assessment: Chart.js is a well-known, industry-standard visualization library. Its inclusion for the purpose of data visualization in a user-generated report is a standard practice and does not represent a malicious external dependency.

expansive-inquiry