ccc

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to ingest content from the local codebase, creating an attack surface where instructions embedded in code could influence agent behavior. Ingestion points: Code snippets and file content retrieved via ccc search and file reading tools. Boundary markers: The instructions do not specify any delimiters or warnings to ignore commands found within the indexed files. Capability inventory: Access to the ccc command suite and file system reading via sed or editor tools. Sanitization: None documented.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the cocoindex-code package from a public registry.
  • [COMMAND_EXECUTION]: The skill suggests using the sed command as a fallback method to read specific line ranges from files for context extraction.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 06:53 PM