find-gaps

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes user-provided artifacts through subagents without explicit boundary markers or sanitization, which could allow malicious instructions in the artifacts to influence subagent behavior.
  • Ingestion points: Artifact paths and their contents are passed to 'general-purpose' subagents in Step 2.
  • Boundary markers: None are specified to distinguish artifact content from instructions or to warn the subagents to ignore embedded prompts.
  • Capability inventory: The skill dispatches general-purpose subagents and invokes additional 'triage' and 'second-opinion' skills via the Skill tool.
  • Sanitization: No validation, filtering, or escaping of artifact content is implemented before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 03:52 PM
Security Audit — agent-trust-hub — find-gaps