document-signing
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external, potentially untrusted documents and attachments to extract signing fields and provisions.
- Ingestion points: The skill reads and reviews 'supplied or already accessible' documents, 'exhibits', and 'attachments' (SKILL.md).
- Boundary markers: The skill relies on an external
<confirmation_policy>for authorization but does not define explicit delimiters or instructions for the agent to ignore command-like text embedded within documents. - Capability inventory: The skill is authorized to perform high-impact actions including 'uploading documents', 'entering sensitive signer data', 'creating envelopes', and 'sending' signing packets via third-party providers.
- Sanitization: There is no evidence of sanitization or filtering logic applied to the content of the documents before the agent processes them for summaries or field mapping.
Audit Metadata