The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a local shell script scripts/scan-fingerprints.sh to perform its primary function. This script uses standard Linux utilities like find and grep to locate potential data leaks. The script is designed for local execution and does not perform network operations or privilege escalation.
[DATA_EXPOSURE]: This skill is a security-focused tool designed specifically to mitigate data exposure. It provides a comprehensive catalog of patterns (internal paths, cloud regions, and vendor URLs) to help the agent identify and redact information before sharing artifacts externally.
[SAFE]: The skill demonstrates high security awareness by mandating the use of RFC-2606 reserved domains (example.com) and RFC-5737 reserved IP ranges for placeholders, ensuring that scrubbed content cannot accidentally resolve or route to real services.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted user-provided repositories and files.
Ingestion points: User-specified files or directories are scanned by the scripts/scan-fingerprints.sh script and subsequently read by the agent for triaging and replacement.
Boundary markers: None identified. The instructions do not specify the use of delimiters when reading target files.
Capability inventory: The skill executes local shell scripts and is expected to perform file-write operations to redact identified fingerprints.
Sanitization: There is no explicit sanitization of the content found within user-provided files before the agent processes it.

generic-by-design