kai-content-batching
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes internal Python scripts to register content in an editorial calendar (
scripts/campaigns/calendar.py) and to perform automated quality gating (scripts/quality_gates/four_us_score.py,scripts/quality_gates/banned_word_check.py,scripts/quality_gates/seo_lint.py). - [EXTERNAL_DOWNLOADS]: Fetches information from external URLs via an internal data collection script (
scripts.audit.collect) to build a proof inventory for marketing content. This process is documented as a data collection step and does not involve executing external code. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from project files and external websites, which represents an indirect injection surface.
- Ingestion points: The skill reads local project files (such as
package.json,README.md) and scrapes data from external URLs provided in the content strategy context. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are specified for the external data ingestion.
- Capability inventory: The skill possesses the ability to execute local scripts and write to the
workspace/directory. - Sanitization: The skill does not explicitly detail any sanitization or validation of external site content before it is processed by the agent.
Audit Metadata