operationalize
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructional logic for a documentation workflow. It lacks network access and does not interact with system-level resources or sensitive files.
- [DATA_EXPOSURE]: File access is restricted to reading from
.agents/research/and writing to.agents/operationalize/. These paths are localized to the agent's workspace and represent intended behavior for data processing. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: Reads content from potentially untrusted research artifacts in
.agents/research/*.md(referenced in SKILL.md). - Boundary markers: No explicit delimiters or 'ignore instructions' warnings are used when processing the input artifacts.
- Capability inventory: The skill produces markdown rule packets and stubs intended for use by other internal builders (
skill-builder,workflow-builder,cc-hooks); it does not execute these external skills itself. - Sanitization: No evidence of input validation, escaping, or filtering of the research data being distilled.
Audit Metadata