The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/gather.py script executes shell commands using subprocess.run to interact with the gh (GitHub) and git CLI tools. While these are used for the skill's core functionality, any command execution on the host machine presents a potential attack surface.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple sources, including GitHub PR titles, commit messages, and local AI session history (Claude, Codex, OpenCode).
Ingestion points: scripts/gather.py reads data from GitHub API calls and local session log files (.jsonl and SQLite DB) as described in SKILL.md Step 1.
Boundary markers: The instructions in SKILL.md lack explicit boundary markers or "ignore instructions" directives for the ingested content.
Capability inventory: The skill has the ability to execute shell commands (via gh and git) and read local session history files.
Sanitization: No sanitization or filtering is performed on the ingested text in scripts/gather.py before it is presented to the agent for summarization.

standup