prospeo-full-export
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from an external API, which acts as an untrusted ingestion point.
- Ingestion points: Lead data (names, titles, industries) is retrieved from the
https://api.prospeo.io/search-personendpoint as described inSKILL.md. - Boundary markers: The skill does not define specific boundaries or "ignore instructions" markers when passing sampled lead data to the
/icp-prompt-buildercomponent mentioned in the documentation. - Capability inventory: The skill utilizes file system write capabilities (
writeFileSync) and network operations (fetch) via the generated script. - Sanitization: The script includes
escapeCSVfor format integrity, but lacks sanitization or validation to filter potential instructions embedded within the lead data itself. - [DYNAMIC_EXECUTION]: The skill instructs the agent to create and run a local TypeScript script based on a provided template to manage API interactions and pagination.
- [COMMAND_EXECUTION]: The process requires the agent to execute shell commands to run the generated script via
tsx, interacting with the local runtime environment.
Audit Metadata