content-factory-dispatcher

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The dispatcher skill creates an indirect prompt injection surface by consuming and processing the outputs of multiple sub-agents (e.g., data collectors, researchers, and writers) in a multi-step pipeline.
  • Ingestion points: The agent reads data from hotpool.json, topics.json, and various files in the drafts/ directory which are populated by other modules.
  • Boundary markers: Absent. The dispatcher lacks instructions to treat ingested data as untrusted or to ignore any embedded instructions within the content it processes.
  • Capability inventory: The skill manages an orchestration loop that triggers other agent skills (such as content-creator and seo) and performs file operations within the ~/clawd/projects/content-factory-agents/output/ directory.
  • Sanitization: No sanitization or validation logic is defined to check the integrity of the data passed between stages in the Ralph CEO loop.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 01:18 AM