documenso-core-workflow-a

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill reads local files using 'fs.readFileSync' and 'node:fs.openAsBlob' and transmits their content to the Documenso service at 'app.documenso.com'. This data flow is expected for the skill's primary purpose of electronic document signing.\n- [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by ingesting untrusted data—specifically recipient names, emails, and file paths—which are then interpolated into API calls and file system operations.\n
  • Ingestion points: Parameters for document creation and recipient management functions located in 'SKILL.md' and 'references/implementation-guide.md'.\n
  • Boundary markers: No delimiters or instructions to ignore embedded commands are present in the code examples.\n
  • Capability inventory: The skill possesses capabilities for local file reading and external network requests to 'app.documenso.com'.\n
  • Sanitization: There is no evidence of input validation, sanitization, or escaping of external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 12:14 PM