The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the execution of several shell commands to gather project data and verify code quality. Evidence: The instructions direct the agent to use git log and git diff for tracking progress, and to run verification tools such as lint, typecheck, and tests during the delivery closure process (SKILL.md).
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting data from the project environment. 1. Ingestion points: The skill reads output from git log, git diff, and existing markdown status files in the planning/ directory (SKILL.md). 2. Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potential commands embedded in the ingested logs or files. 3. Capability inventory: The skill possesses the capability to write files to the repository and execute various shell commands. 4. Sanitization: No sanitization or filtering of the data retrieved from the local repository is specified before it is processed by the agent.

agile-status