argos-cli

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for executing various CLI commands through the argos tool, such as argos upload, argos finalize, and argos build review. These commands are standard operations for the visual regression service.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the vendor's official domains, including app.argos-ci.com and cdn.argos-ci.com. These interactions are used to fetch build metadata, retrieve snapshot diffs, and upload screenshot assets to the Argos platform.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes data (such as build status and snapshot metadata) retrieved from the Argos API.
  • Ingestion points: External data enters the context through argos build get --json and argos build snapshots --json (as described in references/build.md).
  • Boundary markers: None explicitly defined in the output processing instructions.
  • Capability inventory: The agent can execute shell commands via the argos CLI (defined in SKILL.md).
  • Sanitization: No specific sanitization or filtering of API-returned strings is required by the current instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 04:36 PM
Security Audit — agent-trust-hub — argos-cli