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 searchand 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 theccccommand suite and file system reading viasedor editor tools. Sanitization: None documented. - [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the
cocoindex-codepackage from a public registry. - [COMMAND_EXECUTION]: The skill suggests using the
sedcommand as a fallback method to read specific line ranges from files for context extraction.
Audit Metadata