spec-review

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external documents to construct subagent prompts, creating a surface for indirect prompt injection.
  • Ingestion points: The skill reads a 'target document' as part of its primary workflow described in SKILL.md.
  • Boundary markers: Absent. There are no instructions to wrap the document content in delimiters or include warnings to ignore embedded instructions.
  • Capability inventory: The skill has the capability to 'Spawn a fresh general-purpose subagent' using a generated prompt.
  • Sanitization: Absent. No mention of sanitizing, escaping, or validating the document content before it is interpolated into the subagent's prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 04:30 AM
Security Audit — agent-trust-hub — spec-review