founder-operations

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown documentation and YAML configuration. There are no executable scripts, shell commands, or external dependencies.
  • [PROMPT_INJECTION]: The skill is designed to process external inputs referred to as 'evidence' and 'consequential inputs'. While this presents an indirect injection surface, the skill implements robust procedural mitigations.
  • Ingestion points: The main workflow in SKILL.md processes inputs to be categorized based on source and confidence.
  • Boundary markers: The instructions require explicit classification of inputs but do not define technical delimiters.
  • Capability inventory: The skill has no defined tools or script execution capabilities, which prevents instructions in data from triggering automated actions.
  • Sanitization: The operating rules in SKILL.md explicitly mandate the removal of identities, credentials, and private URLs from outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 10:09 PM
Security Audit — agent-trust-hub — founder-operations