The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process untrusted external inputs such as "source material," "product updates," or "loose topics" to generate content briefs.
Ingestion points: Untrusted data enters the agent context through the instructions to "Inspect supplied source material" and "Extract known decisions" in SKILL.md.
Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to differentiate between the user's provided data and the skill's operational instructions, which could lead to the agent following instructions embedded within the source material.
Capability inventory: The skill is limited to text analysis and generation; it does not utilize sensitive system tools, network access, or file-writing capabilities across its instructions.
Sanitization: There is no evidence of sanitization, filtering, or validation logic for the external content before it is interpolated into the agent's workflow.

content-plan