skills/ruvnet/ruflo/browser-replay/Gen Agent Trust Hub

browser-replay

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx -y to download and execute ruvector@0.2.25 and @claude-flow/cli@latest from the npm registry. These are utilized for managing session status and retrieving selectors from memory.- [COMMAND_EXECUTION]: Shell commands are executed via the Bash tool to interface with the session management CLI (rvf status) and perform memory searches for similar selectors.- [REMOTE_CODE_EXECUTION]: The skill performs browser automation that includes executing arbitrary JavaScript via mcp__claude-flow__browser_eval, with the execution logic driven by data found in the external trajectory.ndjson file.- [PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill ingests and acts upon untrusted data from an external trajectory file.
  • Ingestion points: Reads trajectory steps from trajectory.ndjson using the Read tool.
  • Boundary markers: None provided; the skill is instructed to iterate through and execute each step in the trajectory.
  • Capability inventory: Includes powerful browser tools (browser_eval, browser_fill) and shell command execution via Bash.
  • Sanitization: There is no validation or sanitization performed on the actions or arguments loaded from the trajectory file.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 09:12 PM