lucidchart-core-workflow-b
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill's description in the YAML frontmatter refers to "Data-Linked Diagrams," while the content of the instructions describes "Collaboration & Sharing." This inconsistency could lead to confusion regarding the skill's actual capabilities and intended use cases.
- [INDIRECT_PROMPT_INJECTION]: The skill implements a workflow for reading and displaying document comments from the Lucidchart API, which is an untrusted external source.
- Ingestion points: Document comments are retrieved via
client.documents.comments.listin Step 3 ofSKILL.md. - Boundary markers: The instructions lack delimiters or explicit warnings for the agent to treat fetched comment text as untrusted content.
- Capability inventory: The skill allows access to
Read,Write,Edit,Bash, andGreptools. - Sanitization: No sanitization or validation logic is provided for the comment text before it is logged or processed by the agent.
Audit Metadata