processon-diagram
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to ingest and process untrusted external data such as source code and documents to generate diagram models.
- Ingestion points: The workflow in
SKILL.mdinstructs the agent to inspect source code or documents provided by the user to extract facts for modeling. - Boundary markers: The instructions do not specify explicit delimiters (e.g., triple backticks or XML tags) to isolate the external content from the agent's core logic.
- Capability inventory: The skill acts as a modeling layer that passes data to a downstream tool (
processon-prompt); it does not possess direct file-writing, network-access, or command-execution capabilities within the provided files. - Sanitization: The skill contains robust sanitization instructions, explicitly forbidding the inclusion of credentials, local file paths, or private identifiers in the generated output.
Audit Metadata