The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands to interact with the environment, including git config --get remote.origin.url to verify the repository host and a script placeholder {SCRIPT} from the repository root to parse project data.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local repository, which serves as a vulnerability surface for indirect prompt injection:
Ingestion points: Reads .specify/extensions.yml, tasks.md, and /memory/constitution.md (SKILL.md).
Boundary markers: None identified to delimit or neutralize instructions embedded within these files (SKILL.md).
Capability inventory: Uses EXECUTE_COMMAND for hooks, executes shell scripts, and uses the GitHub MCP server to create issues (SKILL.md).
Sanitization: No explicit sanitization or validation of the content retrieved from these project files before it influences execution or is passed to tools (SKILL.md).
[DYNAMIC_EXECUTION]: The skill implements a pre- and post-execution hook mechanism that dynamically identifies and executes commands found in the .specify/extensions.yml file under hooks.before_taskstoissues and hooks.after_taskstoissues keys. Mandatory hooks are automatically invoked using the EXECUTE_COMMAND pattern.

speckit-taskstoissues