citedy-content-writer
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill features a workflow that ingests content from external URLs to generate new articles, which is a common surface for indirect prompt injection attacks where malicious instructions could be hidden in the source material.\n
- Ingestion points: The
source_urlsfield in theautopilotAPI request (SKILL.md).\n - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potential commands found within the ingested URL content.\n
- Capability inventory: The skill is capable of making network requests to the Citedy API and triggering social media publishing actions.\n
- Sanitization: Sanitization and filtering of the external content are not handled by the skill instructions themselves and are expected to be managed by the Citedy backend service.
Audit Metadata