The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses hidden instructions to steer the agent's behavior, specifically instructing it to hide internal validation steps from the end-user.
Evidence: Step 6 in SKILL.md contains the instruction "Do not flag the checklist to the user — just ensure the output passes."
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it interpolates user-provided data into generated prompts for subsequent execution without sanitization.
Ingestion points: The niche, product, and goal fields in the Input Schema (SKILL.md).
Boundary markers: Absent. No delimiters or instructions are provided to prevent the agent from obeying instructions embedded in these fields.
Capability inventory: The skill has no direct code execution but generates invocation_prompt strings for other skills to execute.
Sanitization: Absent. The skill provides no validation or escaping for external content before interpolation.
[NO_CODE]: The skill consists exclusively of Markdown documentation and does not contain any executable scripts, binaries, or automated code installation commands.

funnel-planner