The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from GitHub issues, pull requests, and comments, which are untrusted external sources controlled by third parties.
Ingestion points: Data is fetched via gh api, specifically issue comments and pull request summaries referenced in the "Detailed Summaries" section.
Boundary markers: None present. The skill does not provide delimiters or instructions for the agent to ignore potentially malicious instructions embedded in the GitHub data.
Capability inventory: The skill uses git remote, gh api, and writes reports to the local file system.
Sanitization: No sanitization, escaping, or filtering of external content is specified before the agent summarizes or previews the data.
[COMMAND_EXECUTION]: The skill executes shell commands to gather environment context and fetch external data.
Evidence: Uses git remote -v to determine repository context and gh api to interact with GitHub. These are standard operations for the skill's stated purpose.

repo-activity