stripe-projects

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Runs Stripe CLI commands via the terminal tool to manage project infrastructure, billing, and credential rotation as described in the procedure section of SKILL.md.
  • [EXTERNAL_DOWNLOADS]: Directs the agent to guide the user to install the Stripe CLI and the 'projects' plugin from official and well-known Stripe documentation and registries.
  • [PROMPT_INJECTION]: Identifies an indirect prompt injection surface where user-provided provider and service names are used in shell commands.
  • Ingestion points: User-provided provider and service arguments used in the 'stripe projects add' command in SKILL.md.
  • Boundary markers: Absent; there are no specified delimiters or instructions to the agent to ignore potentially malicious embedded content in user input.
  • Capability inventory: The skill uses the terminal tool which provides full shell command execution capabilities.
  • Sanitization: Absent; no validation, escaping, or filtering of the user-supplied provider strings is mentioned before they are passed to the shell command.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 06:05 AM
Security Audit — agent-trust-hub — stripe-projects