The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell scripts scripts/detect-plan-context.sh and scripts/analyze-impact.sh to perform git repository analysis and environment detection.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface due to the automated processing of external data.
Ingestion points: Fetches untrusted data from GitHub issue descriptions using the gh command-line tool.
Boundary markers: The skill does not implement clear delimiters or instructions to the agent to disregard instructions potentially embedded within the fetched issue content.
Capability inventory: The skill is equipped with high-impact capabilities including Bash command execution, Write operations to the filesystem, and the ability to spawn sub-agents for exploration.
Sanitization: There is no evidence of sanitization, filtering, or validation of the retrieved issue body before it is integrated into the agent's context for plan generation.

plan-viz