compliance-readiness
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes several internal Python scripts (
framework_selector.py,cross_framework_mapper.py,evidence_pool_generator.py, andaudit_simulator.py) located in the relative path../../skills/compliance-os/scripts/. These executions are intended for processing compliance programs. - [PROMPT_INJECTION]: This skill possesses an indirect prompt injection surface due to the way it processes external data.
- Ingestion points: Untrusted data enters the agent context via input files such as
profile.json,program.json, andscope.json(referenced inSKILL.md). - Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore instructions embedded within the contents of the processed JSON files.
- Capability inventory: The skill uses subprocess calls to execute multiple Python scripts (
framework_selector.py,cross_framework_mapper.py, etc., inSKILL.md) which process the ingested files. - Sanitization: There is no evidence of validation, escaping, or filtering of the external JSON content before it is interpolated into the script arguments or processed by the agent.
Audit Metadata