skills/outlinedriven/outline-driven-development/automatic-cybernetic-flow-design/Gen Agent Trust Hub
automatic-cybernetic-flow-design
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate design documents and write them to local file paths. This interaction pattern creates a vulnerability surface where adversarial content in the system description could influence the agent's behavior.
- Ingestion points: The skill ingests untrusted 'interactive system descriptions' as a primary required input.
- Boundary markers: There are no defined delimiters or instructions to ignore embedded commands within the ingested system description data.
- Capability inventory: The skill possesses the capability to write to the local file system at a path specified by the user.
- Sanitization: No validation or sanitization logic is provided for the input content or the user-defined output file path.
- [NO_CODE]: The skill consists exclusively of instructional markdown and configuration files, with no executable scripts or binaries included in the package.
Audit Metadata