reward-sciences
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the
@membranehq/clipackage from the public NPM registry to interact with the Membrane platform. - [COMMAND_EXECUTION]: Uses the
membraneCLI to perform operations such as listing connections, searching for actions, and running API requests against Reward Sciences. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from Reward Sciences APIs.
- Ingestion points: External data retrieved from Reward Sciences endpoints (e.g., Campaigns, Users, Rewards) via
membrane action runormembrane request(SKILL.md). - Boundary markers: None; the skill does not specify any delimiters or safety markers to isolate untrusted data from instructions.
- Capability inventory: The skill has the capability to run actions and proxy network requests through the
membraneCLI (SKILL.md). - Sanitization: No sanitization or validation of data from the external service is mentioned.
Audit Metadata