production-work-units
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data sources, including creative-production specifications and project plans, to generate work units. These inputs could potentially contain malicious instructions designed to influence the agent's logic or output.
- Ingestion points: Reads
../../references/PRODUCTION_WORK_UNITS.mdand user-provided project plans or creative specs. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided for the input data.
- Capability inventory: The skill has the ability to execute shell commands (
scripts/work_units.py) and perform file system writes (00_project/work_units.json). - Sanitization: No sanitization or validation of the input text content is mentioned before processing.
- [COMMAND_EXECUTION]: The skill instructions require the agent to execute specific commands to validate work units.
- Evidence: Usage of
scripts/work_units.py validateandfrontierduring the workflow execution. These are local tools provided with the skill.
Audit Metadata