The Agent Skills Directory

[SAFE]: The skill is a defensive tool intended for auditing applications for insecure configurations and hardcoded secrets. It is an adaptation of reputable open-source security research and no malicious code or unauthorized data access patterns were identified.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run standard local auditing commands like grep and find to scan for vulnerability patterns in the codebase.
[PROMPT_INJECTION]: The instructions establish a clear persona for security analysis without attempting to bypass safety guardrails or override system instructions. As the skill analyzes untrusted code, it possesses an inherent indirect prompt injection surface.
Ingestion points: Source code and configuration files are accessed using Read, Glob, and Grep tools.
Boundary markers: The instructions do not define specific delimiters or 'ignore' blocks for the analyzed content.
Capability inventory: The agent has access to Bash, Read, Write, Edit, Glob, and Grep tools.
Sanitization: No explicit sanitization or filtering of the analyzed content is performed prior to processing.
[DATA_EXFILTRATION]: No network-capable tools or exfiltration patterns were detected; the skill's operations are restricted to the local environment.
[EXTERNAL_DOWNLOADS]: The skill does not perform any remote downloads or external resource fetching. All auditing logic is embedded within the provided documentation and scripts.

insecure-defaults