The Agent Skills Directory

[COMMAND_EXECUTION]: The skill operates by executing various subcommands of the ghcrawl CLI tool, such as sync, refresh, embed, and cluster. These commands manage a local SQLite database and interact with external APIs.
[PROMPT_INJECTION]: The skill is exposed to indirect prompt injection because it ingests and processes untrusted data from GitHub issues and pull requests.
Ingestion points: External data enters the system through the ghcrawl sync and ghcrawl refresh commands, which fetch content from GitHub repositories (documented in SKILL.md).
Boundary markers: The skill instructions lack explicit boundary markers or delimiters to differentiate between system instructions and the content retrieved from GitHub.
Capability inventory: The skill possesses the capability to execute shell commands and perform network operations via the ghcrawl utility.
Sanitization: There is no evidence of sanitization or filtering of the fetched GitHub data before it is used for generating LLM summaries or embeddings.

ghcrawl-cluster-operator