The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local helper scripts ${CLAUDE_PLUGIN_ROOT}/scripts/helpers/check-providers.sh and ${CLAUDE_PLUGIN_ROOT}/scripts/helpers/check-versions.sh to gather data on provider availability and software versions. These operations appear consistent with the stated purpose of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill processes and summarizes external output from system scripts, creating a potential surface for indirect injection if the local environment generates malicious output.
Ingestion points: Output from the check-providers.sh and check-versions.sh scripts referenced in SKILL.md.
Boundary markers: None identified in the prompt instructions to delimit script output from agent instructions.
Capability inventory: Executes shell scripts to retrieve provider metadata.
Sanitization: No explicit sanitization or validation of the script output is performed before summarization.

provider-health