The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local shell script scripts/run-sast.sh for automated setup. It also utilizes several command-line tools including pip, docker, gh, and codeql to install extensions, run containers, and create databases.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, including repository source code and SARIF (Static Analysis Results Interchange Format) scan results, which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Repository source code and SARIF result files (SKILL.md).
Boundary markers: None identified in the provided instructions.
Capability inventory: Execution of a bundled shell script and various CLI tools for package management and container orchestration.
Sanitization: No specific sanitization or validation protocols for the external content are mentioned.

sast-configuration