performance
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python utility script at
.claude/scripts/code_graphto perform code structural analysis, trace execution paths, and identify call frequencies. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. 1. Ingestion points: It reads project source code, domain entity catalogs, and external profiling data. 2. Boundary markers: It lacks explicit delimiters or instructions to ignore embedded commands within the analyzed data. 3. Capability inventory: The agent has the ability to execute shell commands (via the Python script) and perform file system writes to generate reports. 4. Sanitization: No sanitization or validation of the processed code or metrics is mentioned, which could allow malicious comments or data to influence agent behavior.
Audit Metadata