The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git commit messages, sprint reports, and design documents.\n
Ingestion points: Phases 2 and 3 in references/claude-skill.md read repository history and project files.\n
Boundary markers: The instructions do not define clear delimiters or warnings to ignore instructions embedded within the processed content.\n
Capability inventory: The skill utilizes the Write tool to modify files and the Bash tool for shell commands.\n
Sanitization: There is no evidence of sanitization of the content extracted from external sources.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute git commands (git rev-parse, git log) to gather information about the repository.

changelog