studio

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted user input to determine which external instruction sets to load and execute.
  • Ingestion points: User input provided after the /studio command is directly processed for intent classification as seen in SKILL.md.
  • Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore embedded commands within the user's task description.
  • Capability inventory: The skill has access to file system tools (Read, Glob, Grep) and is explicitly instructed to "follow the agent's instructions" once a file is loaded from the agents/ directory (SKILL.md, Rule 1).
  • Sanitization: No sanitization, validation, or escaping of external content is performed before interpolation into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 11:58 AM
Security Audit — agent-trust-hub — studio