panda-doc-upload-docs
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the user and external sources which is then transmitted to the PandaDoc API, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill accepts user-provided data for
recipients,tokens(template variables),metadata, and binary PDFfiledata as described inSKILL.md(Sections 3.1, 3.2, and 7). - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from interpreting instructions that might be embedded within the template tokens or document metadata.
- Capability inventory: The skill utilizes network capabilities to interact with
api.pandadoc.comusingPOST,GET, andDELETEmethods. - Sanitization: The instructions do not specify any validation, escaping, or sanitization requirements for the data before it is interpolated into the JSON payloads sent to the API.
Audit Metadata