The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run standard development commands such as git log for data collection, and lint, typecheck, and tests for delivery verification in the closure mode. These commands are essential for the skill's primary function.
[DATA_EXPOSURE]: The agent is prompted to access local project files, including plans, stories, and git history, to consolidate status reports. This data access is aligned with the stated purpose of the skill and does not involve exfiltration to external domains.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes data from external sources (e.g., git commit messages or project file content) which could potentially contain malicious instructions.
Ingestion points: Data enters the context through the $ARGUMENTS variable and by reading external files such as plans, stories, and git logs (referenced in SKILL.md).
Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to ignore embedded commands within the processed data.
Capability inventory: The skill has the capability to execute shell commands (lint, typecheck, tests, git) based on instructions in SKILL.md.
Sanitization: There are no instructions provided for sanitizing or validating the input data before it is used to generate reports or passed to verification tools.

agile-status