prismatic-integrations
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user requirements and external API documentation to generate integration code.
- Ingestion points: User integration requirements and official service documentation (SKILL.md).
- Boundary markers: No delimiters or specific warnings for untrusted data identified.
- Capability inventory: Shell command execution (prism, npm) and local module execution (SKILL.md).
- Sanitization: No evidence of input sanitization or validation.
- [DYNAMIC_EXECUTION]: Local execution of the compiled integration module occurs during validation.
- Evidence: The prism integrations validate command executes the project module locally as noted in SKILL.md.
- [COMMAND_EXECUTION]: Scaffolding and platform management tasks require shell command execution.
- Evidence: SKILL.md references prism integrations:init, npm install, and various prism platform commands.
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation and example integrations from the vendor's official repositories.
- Evidence: References to prismatic.io documentation and github.com/prismatic-io/examples in SKILL.md.
Audit Metadata