cco-claudemd
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local JavaScript analyzer script (
claudemd-analyzer.js) using thenoderuntime. This is the intended behavior for processing project files. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads and analyzes content from
CLAUDE.mdfiles which could contain malicious instructions. - Ingestion points: Reads user-controlled
CLAUDE.mdfiles from the project directory. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill definition.
- Capability inventory: The skill is allowed to use
Bash,Read, andEdittools, allowing for command execution and file modification. - Sanitization: No explicit sanitization or validation logic for the ingested file content is defined in the instruction set.
Audit Metadata