The Agent Skills Directory

[COMMAND_EXECUTION]: The utility script scripts/generate_config.py generates shell scripts by interpolating raw content into a template and then uses chmod(0o755) to grant execution permissions to the generated file. This pattern is standard for the skill's purpose but represents a potential escalation path if the input content is maliciously crafted.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted configuration parameters to generate executable artifacts.
Ingestion points: External configuration data provided via CLI arguments (--content, --config) to the scripts/generate_config.py script, as well as data processed according to the instructions in SKILL.md.
Boundary markers: Absent. The skill does not define delimiters or provide instructions for the agent to ignore potentially malicious embedded commands in the processed configuration data.
Capability inventory: The skill has access to sensitive tools including Bash (scoped to cloud and nginx environments), Write, and Edit, which could be abused if the generated scripts are executed with higher privileges.
Sanitization: There is no evidence of input validation, escaping, or sanitization within the generation script to prevent command injection within the generated shell scripts.

configuring-load-balancers