The Agent Skills Directory

[COMMAND_EXECUTION]: The skill specifies the use of the bash tool for executing commands, running tests, and reading logs, providing the agent with broad execution capabilities within the project environment.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its design of processing external project data using powerful tools without explicit safety boundaries.
Ingestion points: Reads project files, git history, and system logs through the File ops, git, and bash tools.
Boundary markers: Absent. There are no instructions for the agent to use delimiters or to disregard instructions found within the files it reads.
Capability inventory: Includes bash for shell command execution, git for repository management, and File ops for reading and writing files.
Sanitization: Absent. The skill does not provide logic or instructions to validate or sanitize content ingested from the external environment before processing it.

pm-sprint