capture

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user data which presents an indirect prompt injection surface.
  • Ingestion points: User input provided via the /capture <content> command is directly passed to the storage tool in SKILL.md.
  • Boundary markers: The skill does not define delimiters or provide instructions for the agent to treat the captured content as data rather than executable instructions.
  • Capability inventory: The skill is authorized to use several memory management tools (mcp__plugin_origin_origin__capture, recall, etc.) and the Bash shell tool.
  • Sanitization: The instructions do not specify any validation or sanitization of the user-provided content before storage or subsequent recall.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 07:51 AM
Security Audit — agent-trust-hub — capture