clip-context-mode

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use standard command-line tools to manage data indexing and retrieval.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing external command outputs, representing a potential surface for indirect prompt injection.
  • Ingestion points: External data enters the context via the output of clip <target> <command>.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are defined in the markdown.
  • Capability inventory: The agent can search, list, and purge indexed data using the clip CLI.
  • Sanitization: The skill does not specify any sanitization or validation of the command outputs being indexed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 05:24 PM