transitions-agent

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses npx to execute the transitions-agent CLI tool for several automated workflows including scanning the codebase, applying code fixes, and initializing CI configuration.
  • [EXTERNAL_DOWNLOADS]: The skill fetches the transitions-agent package from the npm registry at runtime using npx transitions-agent@latest. The tool also communicates with api.transitions.dev to fetch motion recipes and perform fixed-based transformations.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the codebase by processing the JSON output of the scan command.
  • Ingestion points: SKILL.md (via npx transitions-agent --json output processing).
  • Boundary markers: Absent; the agent is instructed to relay results directly to the user.
  • Capability inventory: The skill has the ability to write to files (fix command), create PRs/branches (fix --pr), and modify CI workflows (init-ci command) across all its operational scripts.
  • Sanitization: None mentioned; the agent relies on the CLI's deterministic scan output.
  • [DATA_EXFILTRATION]: The skill accesses sensitive configuration paths to manage its licensing, specifically reading from ~/.transitions-agent.json and the TRANSITIONS_AGENT_LICENSE environment variable. It may also transmit this key to the api.transitions.dev service via the --license flag during fix operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 01:49 AM