The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes external repository data (Dockerfiles, lockfiles, and startup scripts) to generate container configurations. This represents a potential surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: Workflow steps 2 and 7 ingest existing repository files including Dockerfiles, lockfiles, and startup declarations.
Boundary markers: No specific delimiters are defined in the workflow to separate untrusted repository content from instructions.
Capability inventory: The skill executes a local Python script (scripts/inspect-dockerfile.py) to perform static analysis and reads repository metadata.
Sanitization: The skill relies on the LLM's inherent processing of the analyzed text; no explicit sanitization or escaping of file content is performed prior to analysis.
[COMMAND_EXECUTION]: The skill executes a local script scripts/inspect-dockerfile.py using Python 3 to validate Dockerfile quality. The script is bundled with the skill and performs benign regex-based static analysis to detect security issues like root users and exposed secrets.

dockerize-app