content-factory

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill utilizes imperative language ("execute it exactly as written", "authoritative playbook") to define its own instructions as the primary source of truth, which is a pattern often associated with attempts to override agent constraints or system prompts.
  • [PROMPT_INJECTION]: The skill is designed to ingest external data (scouting announcements) which is then used to automate content creation and publishing, establishing an indirect prompt injection surface.
  • Ingestion points: External announcement feeds and field-specific news (SKILL.md).
  • Boundary markers: No specific delimiters or "ignore instructions" markers are defined for the ingested data.
  • Capability inventory: invoke_subagent calls, content generation for blogs/posts/videos, and automated publishing with screenshot verification.
  • Sanitization: No sanitization, filtering, or validation logic is specified for the external content before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 12:21 PM
Security Audit — agent-trust-hub — content-factory