stripe-projects
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the official Stripe CLI via a Homebrew tap (
stripe/stripe-cli/stripe) and utilizes the CLI's internal plugin manager to install theprojectsplugin. These references target a well-known service and are documented as standard setup procedures. - [DYNAMIC_EXECUTION]: During initialization, the
stripe projects initcommand installs a supplementary skill file locally at.claude/skills/stripe-projects-cli/SKILL.md. The agent is instructed to use theSkilltool to invoke this dynamically installed component for subsequent project management tasks. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external commands such as
stripe projects searchandstripe projects catalogto present choices to the user. - Ingestion points: Output from the search and catalog CLI commands in SKILL.md.
- Boundary markers: None; output is parsed directly to suggest complementary services.
- Capability inventory: The skill has shell execution privileges (
Bash) and the ability to invoke other skills. - Sanitization: None described for the JSON output of the catalog search.
- [DATA_EXFILTRATION]: The skill manages project credentials and environment variables. It includes explicit safety instructions to prevent secret leakage, such as only listing variable names in the output table and using secure CLI prompts for value entry rather than printing them in logs or responses.
Audit Metadata