workflow-clean-code-angular
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted source code provided by the user. An attacker could embed malicious instructions within code comments or string literals to influence the behavior of the specialist agents.
- Ingestion points: Source files (.ts, .html, .scss, .spec.ts) are read into the agent's context during the scanning phase in steps/step-01-scan.md.
- Boundary markers: The workflow uses a structured Agent Output Protocol to guide specialist agents, which helps maintain focus, though it does not explicitly instruct agents to disregard instructions found within the code being audited.
- Capability inventory: The skill has significant capabilities, including the ability to edit files and execute shell commands via bash for testing and version control (git commit).
- Sanitization: The skill does not perform sanitization of the input source code before analysis, which is standard for code auditing tools.
- [COMMAND_EXECUTION]: The skill utilizes the bash tool to execute standard development and version control commands. Evidence includes git diff and git diff --cached in steps/step-01-scan.md, and npm run lint, npm run type-check, and npm test in steps/step-03-verify.md. These commands are used for their intended purpose within a development environment and do not pose a threat in this context.
Audit Metadata