clean-code
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The file
sub-skills/agent-script-mapping.mdprovides a directory of Python commands for agents to execute, such aspython .agent/skills/vulnerability-scanner/scripts/security_scan.py .. These commands target local scripts within the agent's environment for auditing purposes. - [PROMPT_INJECTION]:
SKILL.mdcontains strong behavioral directives (e.g., "CRITICAL SKILL", "MANDATORY") intended to enforce specific coding styles and operational consistency. Additionally, the skill creates a surface for indirect prompt injection as defined insub-skills/script-output-handling-read-summarize-ask.md: - Ingestion points: Captured script output parsed by the agent in
sub-skills/script-output-handling-read-summarize-ask.md. - Boundary markers: Absent; there are no specific instructions to ignore potential commands embedded within the script output.
- Capability inventory: The agent is authorized to edit and update project files as described in the "Clean Code" rules in
SKILL.md. - Sanitization: Absent; the agent is instructed to capture and summarize all output without validation or escaping.
Audit Metadata