The Agent Skills Directory

[SAFE]: All core functionalities, including network research and filesystem write operations, are aligned with the skill's stated purpose of content creation and management. No suspicious obfuscation or hidden logic was detected.
[PROMPT_INJECTION]: The skill exhibits an inherent surface for indirect prompt injection because it reads and processes data from external URLs (via WebFetch) and user-provided documents. Ingestion points: Untrusted data enters the agent context through user files in Phase 1, Step 1 and external web content in Step 3. Boundary markers: The instructions do not define specific delimiters or guidelines for the agent to distinguish between its primary instructions and any instructions embedded within the fetched content. Capability inventory: The skill is configured to write generated articles to multiple files on the local filesystem. Sanitization: No explicit sanitization, filtering, or validation of the external content is described before it is used for planning or writing.

content-planner