x9-context-files-generator
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository files like AGENTS.md and README.md which may contain malicious instructions designed to subvert the agent. \n
- Ingestion points: Workflow step 1 in SKILL.md and the 'Preserve' section in agents-md.md. \n
- Boundary markers: The skill lacks formal delimiters to isolate user-supplied content from system instructions. \n
- Capability inventory: The skill can read/write files and execute shell commands for verification. \n
- Sanitization: Safety guidance is provided in SKILL.md to only run safe, local commands and to seek user authority for high-risk actions. \n- [COMMAND_EXECUTION]: The skill is instructed to execute commands discovered in documentation to verify their functionality. \n
- Evidence: The 'Verification' sections in both agents-md.md and readme.md direct the agent to run documented setup or usage commands. \n
- Context: While intended for validation, this provides a mechanism for untrusted data to reach the command line.
Audit Metadata