crypto
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute several command-line security tools, specifically semgrep, bandit, gosec, and gitleaks, to identify vulnerabilities in the targeted source code. These tools are used as intended for security analysis.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) because its primary function involves processing and analyzing untrusted source code from external files.\n
- Ingestion points: Source code files targeted by the user for analysis (e.g., through the --scope flag).\n
- Boundary markers: There are no explicit instructions or delimiters defined to separate the untrusted input data from the agent's logic or to warn the agent about potential instructions embedded in comments or code.\n
- Capability inventory: The agent has the capability to execute external CLI scanners and read files from the system.\n
- Sanitization: No sanitization, filtering, or validation steps are mentioned for the content of the files being analyzed before they are processed by the agent.
Audit Metadata