The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local git and gh (GitHub CLI) commands to fetch repository history, pull request status, and comments. It also includes an optional feature to run a local analysis script from a related skill (sentinel). These operations are consistent with the tool's intended use for development reporting.\n- [INDIRECT_PROMPT_INJECTION]: The skill handles external, user-generated data such as commit messages, PR descriptions, and comments which are considered untrusted input.\n
Ingestion points: Data is collected through git log and gh search commands as defined in the workflow section of SKILL.md.\n
Boundary markers: The skill lacks formal delimiters but instructs the agent to synthesize data rather than repeating it verbatim, providing a natural buffer against instruction following from processed text.\n
Capability inventory: The skill possesses the ability to execute shell commands and write files to the local filesystem via the --doc flag.\n
Sanitization: The skill includes an explicit instruction to summarize content rather than outputting raw data if sensitive information like secrets or tokens are detected in commit or PR bodies.

commit-report