liberating-structure-min-specs

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists entirely of natural language instructions for facilitating a Min Specs session. It contains no scripts, shell commands, binaries, or external code dependencies.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a mechanism for processing user-supplied rule sets. Ingestion points: User input provided during Phase 1 (Brainstorming) and Phase 5 (Final Check). Boundary markers: None (user input is not wrapped in specific delimiters or instructions to ignore sub-prompts). Capability inventory: None (the skill does not define or use any tools, network access, or file system operations). Sanitization: None. Because the agent lacks any actionable capabilities in this context, the ingestion of untrusted data represents a safe surface.
  • [SAFE]: No patterns of obfuscation, malicious prompt injection, or credential exposure were found. The skill is consistent with its stated purpose of facilitating a Liberating Structures exercise.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 11:59 PM
Security Audit — agent-trust-hub — liberating-structure-min-specs