skills/halt-catch-fire/mutiny/p-image/Gen Agent Trust Hub

p-image

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts which are interpolated into shell commands executed via the belt CLI tool.
  • Ingestion points: The prompt value within the JSON input passed to belt app run commands in SKILL.md.
  • Boundary markers: The instructions do not define delimiters or specific markers to isolate the user-provided prompt from the command structure.
  • Capability inventory: The skill leverages the Bash tool to execute system-level commands through the belt CLI.
  • Sanitization: No explicit sanitization or escaping mechanisms are described for handling the user-provided prompt content before it is processed by the CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — p-image