kai-abm
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
four_us_score.pyandbanned_word_check.py) to perform automated quality checks on generated marketing assets. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests content from numerous codebase files that may be influenced by external actors.
- Ingestion points: Reads from
MARKETING.md,CLAUDE.md,README.md,PROJECT.md,package.json, and general landing pages/project files. - Boundary markers: None identified. The skill does not include instructions to delimit or ignore potentially malicious content within these source files.
- Capability inventory: The skill can read/write local files and execute subprocesses via Python validation scripts.
- Sanitization: No explicit validation, escaping, or filtering of the content read from codebase files is performed before processing.
Audit Metadata