The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes user-provided data ('Brand Reader output') which creates a surface for indirect prompt injection. Ingestion points: Data is pasted directly into the prompt in SKILL.md. Boundary markers: None present; the skill lacks delimiters to isolate the untrusted data from the prompt instructions. Capability inventory: No code execution, file system access, or network operations are present across the scripts. Sanitization: None detected. Given the lack of tool access, the risk is localized to the agent's textual response and does not pose a system-level threat.
[NO_CODE]: The skill is composed exclusively of natural language instructions and prompt templates, containing no executable scripts, shell commands, or binary files.

angle-writer