script-writer
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input (video topics, key points) and stores the resulting scripts in a local database file (~/.claude/script_writer.json) for future reference. There are no explicit boundary markers or sanitization steps mentioned in the instructions for handling these inputs.
- Ingestion points: User topic and content requirements provided in Step 3 and Step 6 of SKILL.md.
- Boundary markers: Absent.
- Capability inventory: The skill utilizes scripts/script_db.py to perform local file write operations.
- Sanitization: Absent.
Audit Metadata