The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests data from external files and URLs using the read_file and fetch_url tools without implementing boundary markers or sanitization logic.
Ingestion points: Data enters the context via read_file and fetch_url.
Boundary markers: No delimiters or instructions to ignore embedded commands are present in the prompt instructions.
Capability inventory: The skill possesses write_file, read_file, and fetch_url capabilities.
Sanitization: No input validation or filtering is performed.
[DATA_EXFILTRATION]: The skill utilizes the fetch_url tool to connect to external, non-whitelisted domains for design inspiration, which represents a network-based attack surface.
[NO_CODE]: No executable script files (such as .py or .js) were found in the skill package, which significantly reduces the risk of direct remote code execution or persistence.

markdown-stylist