The Agent Skills Directory

[SAFE]: The skill is a collection of analytical guidelines and checklists for identifying authorization vulnerabilities (STRIDE category E) in source code. It does not contain executable code or harmful instructions.
[INDIRECT_PROMPT_INJECTION]: The skill instructions define a workflow where the agent ingests and analyzes untrusted source code. This represents a potential surface for indirect prompt injection if the analyzed code contains malicious instructions intended to influence the agent's behavior.
Ingestion points: Source code files identified through the --scope flag in SKILL.md.
Boundary markers: The workflow does not explicitly define delimiters to isolate untrusted source code from the agent's system instructions.
Capability inventory: The skill is restricted to analysis and reporting; it does not utilize file-system writes, network operations, or subprocess execution.
Sanitization: The instructions do not specify any sanitization or filtering of the ingested source code content.

privilege-escalation