ai-content-creation
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes a validation script (
scripts/check-output.py) that ingests content from a user-specified file path to check for length and keyword compliance. While this represents a data ingestion surface, the script's capabilities are limited to reading the file and performing basic string matching, which does not pose a significant security risk.\n - Ingestion points:
sys.argv[1]file path inscripts/check-output.py.\n - Boundary markers: None.\n
- Capability inventory: File reading via
Path.read_text().\n - Sanitization: Basic UTF-8 decoding with error replacement.
Audit Metadata