The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes various local development and audit tools including git, rg, ast-grep, npm audit, pip-audit, and cargo audit. These operations are consistent with the skill's documented purpose of performing a technical debt audit and architectural review.
[EXTERNAL_DOWNLOADS]: The documentation provides installation instructions that fetch the skill manifest from the author's GitHub repository (ksimback/tech-debt-skill). This is a standard distribution pattern for agent skills and uses a well-known service.
[PROMPT_INJECTION]: The skill processes untrusted data from the codebase being audited, creating a surface for indirect prompt injection. This is inherent to the functionality of a code analysis tool.
Ingestion points: Processes all files in the current repository, README.md, package manifests, and git log output.
Boundary markers: No specific delimiters or instructions to ignore embedded instructions are used when processing codebase content.
Capability inventory: The skill can execute shell commands (audit tools) and write files (TECH_DEBT_AUDIT.md) based on its analysis.
Sanitization: No explicit sanitization or filtering of the ingested code content is performed before the model analyzes it.

tech-debt-audit