The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) to interact with the GitHub API. Technical analysis of scripts/gh_common.py shows that shell commands are executed using subprocess.run() with a list of arguments, which is a secure practice that prevents shell injection.
[EXTERNAL_DOWNLOADS]: The skill retrieves public data (repository stars, forks, issues, and user profiles) from GitHub's official API. These network operations are necessary for the skill's primary function and target a trusted domain (github.com).
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it ingests untrusted data from external sources.
Ingestion points: Data is collected from GitHub user bios, issue titles, and issue bodies via the GitHub API in scripts/gh_repo_signals.py and scripts/gh_issues_scanner.py.
Boundary markers: The data is exported to structured CSV files (_users.csv, _interactions.csv) before being presented to the agent for analysis.
Capability inventory: The skill has access to the Bash tool and can execute local Python scripts via subprocess calls.
Sanitization: There is no explicit sanitization or filtering of the text content retrieved from GitHub, relying on the agent's internal safety guardrails when interpreting the data.

github-repo-signals