agentsmd-claudemd-generator
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses Bash tools (ls, git, and tree) to survey the repository. These tools are used for inspection purposes to identify project layout and relevant commands.
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks. 1. Ingestion points: It processes README.md, CONTRIBUTING.md, and other documentation files during Phase 1 to identify project philosophy and workflows. 2. Boundary markers: It lacks explicit instructions to ignore or escape instructions found within the repository files. 3. Capability inventory: The skill has Write and Edit capabilities to create AGENTS.md and CLAUDE.md, which include shell command blocks and agent instructions. 4. Sanitization: No sanitization or validation of the identified commands is performed before they are included in the generated output, potentially allowing a malicious repository to influence the agent's future configuration.
Audit Metadata