secret-scanner
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- No Code (SAFE): The skill consists entirely of documentation (README.md and SKILL.md) and does not include any executable scripts, binaries, or automated code components.
- Indirect Prompt Injection (LOW): The skill is designed to process untrusted data (source code and configuration files), which presents a surface for indirect prompt injection. However, its limited toolset (Read, Grep) and primary focus on pattern matching significantly mitigate this risk.
- Ingestion points: Reads local files, git commit data, and environment configurations via the Read and Grep tools.
- Boundary markers: Absent; the skill does not specify the use of delimiters or 'ignore' instructions for processed data.
- Capability inventory: Uses the Read and Grep tools to scan file contents.
- Sanitization: No documentation regarding the sanitization or escaping of the ingested file content.
- Data Exposure & Exfiltration (SAFE): The skill mentions sensitive file paths (e.g., ~/.aws/credentials) and example secrets. These are used solely for scanning and demonstration purposes. No network access or exfiltration mechanisms are present in the skill definition.
Audit Metadata