static-application-security-testing
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to invoke several command-line tools, including Semgrep, CodeQL, and Bandit, to scan source code for vulnerabilities. This behavior is expected given the skill's purpose as a static analysis tool.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted source code repositories which may contain malicious instructions hidden in comments or data.
- Ingestion points: All files within the source code repository provided by the user for scanning (e.g.,
/app). - Boundary markers: None; the skill lacks specific delimiters or instructions to the agent to ignore natural language commands found within the code being analyzed.
- Capability inventory: The skill can execute various CLI-based security tools and generate structured reports based on the code content.
- Sanitization: None; the skill processes the raw contents of the source files without pre-validation or sanitization.
Audit Metadata