planar-binding

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill's primary function is to ingest and process data from external entities like third-party APIs and agents, which creates a surface for indirect prompt injection.
  • Ingestion points: External APIs, cloud services, and third-party agents (SKILL.md).
  • Boundary markers: The procedure suggests defining 'no-touch boundaries' and a 'scope of access', providing conceptual guidance but lacking instructions for technical delimiters or input isolation.
  • Capability inventory: No tool usage or code execution is defined within the skill's own files, relying on the agent's general environment capabilities.
  • Sanitization: The skill lacks explicit instructions for sanitizing or escaping content retrieved from external entities before processing it.
  • [NO_CODE]: The skill consists entirely of markdown instructions and YAML configuration; it does not include any scripts, binaries, or executable code files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 09:14 AM
Security Audit — agent-trust-hub — planar-binding