NYC

knowledge-synthesis

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Prompt Injection (LOW): The skill possesses a surface for indirect prompt injection as it is designed to ingest and process untrusted data from various external sources.
  • Ingestion points: Raw search results from chat, email, cloud storage, and project trackers (SKILL.md).
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or warnings to ignore embedded instructions.
  • Capability inventory: No executable scripts or subprocess commands are defined in this skill.
  • Sanitization: Absent; the skill does not instruct the agent to sanitize or escape data before synthesis.
  • No Code (SAFE): This skill contains purely markdown-based instructions and lacks any functional code, scripts, or binary files, minimizing the risk of direct malware or system compromise.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM