content-distribution
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks detected across the skill files.
- [COMMAND_EXECUTION]: The skill includes a local utility script
scripts/check-output.pydesigned to validate the quality of generated deliverables. This script performs simple string matching and length checks on local files without external network access or privileged operations. - [PROMPT_INJECTION]: The skill processes external user content (articles, podcasts, videos) to create distribution plans, which represents a surface for indirect prompt injection.
- Ingestion points: External content provided to the agent as input for distribution planning.
- Boundary markers: Not present in the instruction set.
- Capability inventory: Local file reads and execution of the included validation script.
- Sanitization: None detected; however, the impact is minimal as the skill's primary focus is content reformatting.
Audit Metadata