suprsend-docs-support
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
sshcommand to connect tosuprsend.sh. This is used to access a virtual filesystem containing documentation, allowing for standard Unix tool interaction (grep, cat, find). As the domain is owned by the vendor (suprsend), this is considered standard functionality for the skill's purpose. - [EXTERNAL_DOWNLOADS]: The skill fetches content from external URLs including
docs.suprsend.comandsuprsend.sh. These resources are official vendor endpoints used for serving raw markdown and bulk documentation files. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external documentation into the agent context. This presents a potential surface for indirect prompt injection if the remote documentation source were to be compromised.
- Ingestion points: Documentation is fetched via SSH from
suprsend.shand via HTTP fromdocs.suprsend.com(documented in SKILL.md). - Boundary markers: None identified in the provided instructions.
- Capability inventory: The skill utilizes
sshfor remote file access and implicitly uses network fetching capabilities for URL-based documentation. - Sanitization: No specific sanitization or filtering of the fetched documentation is mentioned in the skill instructions.
Audit Metadata