to-invariants

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the codebase and conversation context and writes the summarized results to a file, which is a classic surface for indirect prompt injection.
  • Ingestion points: The skill reads the current conversation context and performs a sweep of the codebase (SKILL.md).
  • Boundary markers: There are no explicit boundary markers or instructions to ignore potential commands embedded in the code comments or discussion logs during the extraction process.
  • Capability inventory: The skill possesses file system write capabilities to the path provided in {{ARGUMENTS}} (defaulting to docs/INVARIANTS.md).
  • Sanitization: The instructions do not include steps to sanitize or validate content extracted from the code before writing it to the output document.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 06:17 PM
Security Audit — agent-trust-hub — to-invariants