link-cli
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute the @stripe/link-cli package from a public registry. This is an expected mechanism for using tools provided by established technology services.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands to perform authentication, list payment methods, and retrieve sensitive one-time-use payment credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that could be influenced by a third party, creating a potential surface for indirect prompt injection.
- Ingestion points: Data returned from spend-request retrieve and mpp decode commands as described in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious content within the external data.
- Capability inventory: The agent has the ability to execute shell commands via npx for all listed functionality.
- Sanitization: The skill relies on structured JSON output from the CLI but does not specify additional validation or sanitization steps for the data processed.
Audit Metadata