generation-budget
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script
../../scripts/generation_scheduler.pyfor deterministic state changes and resource checks. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external files and project state, which serves as a potential attack surface for indirect instructions.
- Ingestion points: The agent is instructed to read
../../references/GENERATION_BUDGETING.mdand the current durable project state. - Boundary markers: There are no explicit delimiters or warnings to ignore instructions within the referenced files or project state.
- Capability inventory: The skill has the capability to run a local script (
../../scripts/generation_scheduler.py) based on the ingested state. - Sanitization: The instructions do not specify any validation or sanitization steps for the data retrieved from the project state or reference files.
Audit Metadata