The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes bash scripts located at ${CLAUDE_PLUGIN_ROOT}/skills/*/scripts/update.sh. These scripts are used to perform drift checks and apply updates to vendored packs.
[EXTERNAL_DOWNLOADS]: The update process involves fetching data from howborisusesclaudecode.com. This is a third-party domain that does not belong to a trusted organization or well-known service.
[DATA_EXFILTRATION]: The skill initiates network requests to howborisusesclaudecode.com, which is not a whitelisted domain. While the instructions claim egress is read-only, the ability to connect to arbitrary third-party domains presents a data exposure risk.
[PROMPT_INJECTION]: The skill processes untrusted third-party data in vendor/SKILL.md files.
Ingestion points: Data is read from vendor/SKILL.md (e.g., the boris pack baseline).
Boundary markers: The instructions include a conceptual warning to treat these files as untrusted data and ignore embedded instructions.
Capability inventory: The skill has the capability to execute shell commands (bash) and perform network requests.
Sanitization: There is no evidence of automated sanitization or validation of the fetched content before processing.

update