The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run various industry-standard security auditing tools depending on the detected project stack. Examples include npm audit, composer audit, pip-audit, and cargo audit. These commands are used for their intended purpose of identifying vulnerable dependencies.
[PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it is designed to ingest and analyze untrusted data from a user's codebase and log files. Maliciously crafted content within the analyzed files (e.g., instructions hidden in code comments) could potentially influence the agent's behavior during the triage or investigation process. 1. Ingestion points: Project source code files, configuration files, and application logs. 2. Boundary markers: None provided in the instructions. 3. Capability inventory: File system read access, file system write access (for remediations), and execution of shell commands for dependency auditing. 4. Sanitization: There are no instructions for the agent to sanitize or escape the content of the files it reads before processing them.
[SAFE]: This is a documentation-oriented skill that provides reference materials for security auditing. It does not contain any executable scripts, binaries, or obfuscated content. All security-sensitive functions mentioned in the reference files are provided as examples of vulnerable code patterns for detection or as secure remediation templates.

soc-analyst