codemapper
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions utilize the 'cm' utility to perform various code analysis tasks such as mapping project structure, searching for symbols, and tracing dependencies.
- [PROMPT_INJECTION]: A vulnerability surface for indirect prompt injection exists.
- Ingestion points: The agent reads potentially untrusted data from local source code through commands like
cm query --show-bodyandcm map(SKILL.md). - Boundary markers: None identified in the skill instructions to delimit analyzed code from agent instructions.
- Capability inventory: The skill has the capability to execute filesystem analysis commands (
cm) across the project. - Sanitization: There are no documented sanitization or filtering steps to prevent the agent from following instructions embedded within comments or strings in the analyzed source code.
Audit Metadata