The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references several industry-standard security tools and their official installation methods. These include fetching git-secrets from the official AWS Labs GitHub repository (https://github.com/awslabs/git-secrets.git) and installing tools like truffleHog, detect-secrets, and git-filter-repo via standard package managers like pip. These references target established, well-known organizations and services.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from code repositories, which creates a potential surface for indirect prompt injection. Ingestion points: The agent is instructed to read local files, configuration files (e.g., .env), and git history. Boundary markers: The provided instructions do not include specific delimiters or warnings to the agent to distinguish between data being scanned and instructions. Capability inventory: The skill uses analysis and search tools (like grep, git, and third-party scanners) to process this untrusted data. Sanitization: No explicit sanitization or filtering steps are defined to prevent the agent from potentially executing instructions found within the analyzed files.

secret-scanner