The Agent Skills Directory

[SAFE]: No security issues were detected. The skill consists of text-processing instructions and contains no executable code or network operations.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided article drafts which presents a theoretical attack surface.
Ingestion points: User-provided article content for editing as described in SKILL.md.
Boundary markers: Absent; the instructions do not specify delimiters to separate the article content from the agent instructions.
Capability inventory: None. The skill uses disable-model-invocation: true and does not define any scripts, subprocesses, or network operations.
Sanitization: Absent; the skill does not perform validation or filtering of the processed text.
Note: Because the skill lacks any actionable capabilities (file access, network, or tool execution), this ingestion surface is not exploitable.

edit-article