ray-kb
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script to validate that generated video scripts follow the required format and maintain data integrity.
- Evidence: Instructions in SKILL.md specify running python3 scripts/oral_script_check.py to verify output.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input articles, which presents a surface for indirect prompt injection.
- Ingestion points: The skill reads article content as specified in the Input Gate section of SKILL.md.
- Boundary markers: None present.
- Capability inventory: The agent can read/write local files and execute the included validation script.
- Sanitization: None, however, the skill requires a source_sha256 content fingerprint to ensure integrity between the source article and the generated script.
Audit Metadata