The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines commands such as /generate-article that ingest untrusted data from the user via the [topic] and [context] parameters.
Ingestion points: SKILL.md (via command arguments).
Boundary markers: None present to delimit user input from instructions.
Capability inventory: The skill has no capabilities to execute shell commands, perform network operations, or write to the file system.
Sanitization: No filtering or escaping of input is performed.
[SAFE]: The skill is purely instructional and contains no scripts or binary components. All external references (e.g., flyctl, Spec Kit) are mentioned as topical context for article generation rather than tools for the agent to execute.

article-generator