pointerpro
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
membraneCLI to perform operations such as authentication, action discovery, and API requests. This is the intended mechanism for the skill's functionality. - [EXTERNAL_DOWNLOADS]: The instructions direct the user to install the
@membranehq/cliglobal package from the NPM registry. This is a vendor-owned resource associated with the skill author and is necessary for operation. - [PROMPT_INJECTION]: The skill processes external data from Pointerpro (e.g., respondent answers, survey content), creating a surface for indirect prompt injection.
- Ingestion points: Untrusted data is retrieved via
membrane action runandmembrane requestas documented in SKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish external content from system instructions.
- Capability inventory: The agent can execute CLI commands and perform network requests through the
membraneproxy. - Sanitization: No evidence of sanitization, filtering, or validation of retrieved data is specified in the skill configuration.
Audit Metadata