Skills
Navigate
skills/n0an/vivadicta/screenshot/Gen Agent Trust Hub

screenshot

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied input via the $ARGUMENTS variable and is instructed to follow instructions contained within that data after capturing a screenshot. This establishes a surface where malicious instructions embedded in untrusted data could influence agent behavior.\n
  • Ingestion points: $ARGUMENTS variable in SKILL.md.\n
  • Boundary markers: None explicitly defined to separate data from instructions.\n
  • Capability inventory: Shell command execution including xcrun, mkdir, sed, and axe across SKILL.md and references/advanced.md.\n
  • Sanitization: None present.\n- [COMMAND_EXECUTION]: The skill uses local shell commands to manage the iOS Simulator and the local filesystem for screenshot storage.\n
  • Evidence: Executing xcrun simctl for capturing screenshots and mkdir for directory creation as defined in SKILL.md and references/advanced.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 01:54 AM