Extract Component

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted conversation history to generate new components. This is inherent to its primary purpose of skill extraction.
  • Ingestion points: Conversation history used as the source for component extraction.
  • Boundary markers: No specific delimiters or safety instructions are defined within the skill to differentiate between data and instructions in the history.
  • Capability inventory: The skill triggers the '/skill-extractor:extract' command which is used to generate and save new component files.
  • Sanitization: There is no mention of explicit sanitization or filtering of the ingested conversation data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 04:57 AM