production-coverage
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a Python script (
python scripts/production_coverage.py <project>) to audit project scope. This provides a mechanism for the agent to run code based on the provided project files. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill reads and processes external data from
PRODUCTION_COVERAGE.mdand other screenplay/production artifacts (dialogue cues, blocking, shots) passed via the project argument. - Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its instructions and the data contained within the production files.
- Capability inventory: The skill utilizes shell command execution capabilities to run its audit scripts.
- Sanitization: There is no mention of sanitization or validation of the screenplay or production units before they are processed by the audit tool.
Audit Metadata